{"id":"https://openalex.org/W2893007245","doi":"https://doi.org/10.1109/jproc.2018.2868961","title":"Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators","display_name":"Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators","publication_year":2018,"publication_date":"2018-09-28","ids":{"openalex":"https://openalex.org/W2893007245","doi":"https://doi.org/10.1109/jproc.2018.2868961","mag":"2893007245"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2018.2868961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2018.2868961","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-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":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"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":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3247-1782","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104910026","display_name":"Mark Gates","orcid":"https://orcid.org/0000-0003-2996-1641"},"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":"Mark Gates","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0003-2996-1641","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070456582","display_name":"Jakub Kurzak","orcid":"https://orcid.org/0000-0002-9697-0145"},"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":"Jakub Kurzak","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-9697-0145","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, 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":["Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":"https://orcid.org/0000-0002-0089-6965","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062373552","display_name":"Yaohung M. Tsai","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":"Yaohung M. Tsai","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4422,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84173491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"106","issue":"11","first_page":"2040","last_page":"2055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9839000105857849,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7555538415908813},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7079505920410156},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.6504510045051575},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5844488143920898},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5403213500976562},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5049920678138733},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5042577981948853},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5039209723472595},{"id":"https://openalex.org/keywords/numerical-linear-algebra","display_name":"Numerical linear algebra","score":0.4790281355381012},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.45340341329574585},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.44505205750465393},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4385731518268585},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.43336617946624756},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42507562041282654},{"id":"https://openalex.org/keywords/system-of-linear-equations","display_name":"System of linear equations","score":0.42425429821014404},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24527066946029663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13708704710006714},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.11314067244529724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555538415908813},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7079505920410156},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.6504510045051575},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5844488143920898},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5403213500976562},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5049920678138733},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5042577981948853},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5039209723472595},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.4790281355381012},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.45340341329574585},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.44505205750465393},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4385731518268585},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.43336617946624756},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42507562041282654},{"id":"https://openalex.org/C94523830","wikidata":"https://www.wikidata.org/wiki/Q11203","display_name":"System of linear equations","level":2,"score":0.42425429821014404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24527066946029663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13708704710006714},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.11314067244529724},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":3,"locations":[{"id":"doi:10.1109/jproc.2018.2868961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2018.2868961","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/3aeed3e2-5b4b-425c-9598-9f362ec41503","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/3aeed3e2-5b4b-425c-9598-9f362ec41503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dongarra, J, Gates, M, Kurzak, J, Luszczek, P & Tsai, Y M 2018, 'Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators', IEEE. Proceedings, vol. 106, no. 11, pp. 2040-2055. https://doi.org/10.1109/JPROC.2018.2868961","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/3aeed3e2-5b4b-425c-9598-9f362ec41503","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8476161/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dongarra, J, Gates, M, Kurzak, J, Luszczek, P & Tsai, Y M 2018, 'Autotuning Numerical Dense Linear Algebra for Batched Computation With GPU Hardware Accelerators', IEEE. Proceedings, vol. 106, no. 11, pp. 2040-2055. https://doi.org/10.1109/JPROC.2018.2868961","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6974538609","display_name":null,"funder_award_id":"#1642441: SI2-SSE: BONSAI","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7594707981","display_name":null,"funder_award_id":"#DE-SC0010042","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"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":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W792096099","https://openalex.org/W1046360519","https://openalex.org/W1582138098","https://openalex.org/W1737435842","https://openalex.org/W1964031104","https://openalex.org/W1972209410","https://openalex.org/W1978642402","https://openalex.org/W1997033059","https://openalex.org/W1998492046","https://openalex.org/W2006508316","https://openalex.org/W2006682733","https://openalex.org/W2015262702","https://openalex.org/W2016279572","https://openalex.org/W2063509315","https://openalex.org/W2090698642","https://openalex.org/W2099625934","https://openalex.org/W2101409192","https://openalex.org/W2102182691","https://openalex.org/W2109222446","https://openalex.org/W2118746782","https://openalex.org/W2127906479","https://openalex.org/W2136952590","https://openalex.org/W2138215414","https://openalex.org/W2155942156","https://openalex.org/W2162525251","https://openalex.org/W2169150754","https://openalex.org/W2199814763","https://openalex.org/W2208934446","https://openalex.org/W2410272182","https://openalex.org/W2500595894","https://openalex.org/W2502925949","https://openalex.org/W2562339416","https://openalex.org/W2605732856","https://openalex.org/W2731116490","https://openalex.org/W4239685157","https://openalex.org/W6622860393","https://openalex.org/W6736403352","https://openalex.org/W7052131219"],"related_works":["https://openalex.org/W2035371040","https://openalex.org/W160834089","https://openalex.org/W1488956137","https://openalex.org/W2988894191","https://openalex.org/W2132919497","https://openalex.org/W2522245970","https://openalex.org/W2137144623","https://openalex.org/W2477677129","https://openalex.org/W2001226000","https://openalex.org/W3023718732"],"abstract_inverted_index":{"Computational":[0],"problems":[1],"in":[2,184,215,240,244],"engineering":[3,63],"and":[4,40,60,71,122,212,225,252],"scientific":[5],"disciplines":[6],"often":[7],"rely":[8],"on":[9,31,180],"the":[10,32,46,58,69,72,85,110,115,139,150,159,170,181,185,202,216,236],"solution":[11,160],"of":[12,15,18,35,64,98,101,138,153,161,164,168,176,235],"many":[13,162,226,230],"instances":[14],"small":[16],"systems":[17,100,167],"linear":[19,47,99,165],"equations,":[20],"which":[21,83],"are":[22,78],"called":[23],"batched":[24,151],"solves.":[25],"In":[26],"this":[27,124],"paper,":[28],"we":[29],"focus":[30,175],"important":[33],"variants":[34],"both":[36],"batch":[37,186],"Cholesky":[38],"factorization":[39,70],"subsequent":[41],"substitution.":[42],"The":[43,173,220,233],"former":[44],"requires":[45],"system":[48],"matrices":[49,183],"to":[50,104,129,194],"be":[51],"symmetric":[52],"positive":[53],"definite":[54],"(SPD).":[55],"We":[56,133,196],"describe":[57],"implementation":[59,140],"automated":[61,136],"performance":[62,222],"these":[65,242],"kernels":[66],"that":[67,187],"implement":[68],"two":[73],"substitutions.":[74],"Our":[75,156],"target":[76,95],"platforms":[77],"graphics":[79],"processing":[80,112],"units":[81],"(GPUs),":[82],"over":[84],"past":[86],"decade":[87],"have":[88,188],"become":[89],"an":[90,135],"attractive":[91],"high-performance":[92],"computing":[93],"(HPC)":[94],"for":[96,149,229],"solvers":[97,200,204],"equations.":[102],"Due":[103],"their":[105],"throughput-oriented":[106],"design,":[107],"GPUs":[108],"exhibit":[109],"highest":[111],"rates":[113],"among":[114],"available":[116,214],"processors.":[117],"However,":[118],"without":[119],"careful":[120],"design":[121],"coding,":[123],"speed":[125],"is":[126,179,223],"mostly":[127],"restricted":[128],"large":[130],"matrix":[131,249],"sizes.":[132],"show":[134],"exploration":[137],"space":[141],"as":[142,144,206],"well":[143],"a":[145,245],"new":[146],"data":[147],"layout":[148],"class":[152],"SPD":[154,166],"solvers.":[155],"tests":[157],"involve":[158],"thousands":[163],"exactly":[169],"same":[171],"size.":[172],"primary":[174],"our":[177,198],"techniques":[178],"individual":[182],"dimensions":[189],"ranging":[190],"from":[191],"5-by-5":[192],"up":[193],"100-by-100.":[195],"compare":[197],"autotuned":[199],"against":[201],"state-of-the-art":[203],"such":[205],"those":[207],"provided":[208],"through":[209],"NVIDIA":[210],"channels":[211],"publicly":[213],"optimized":[217],"MAGMA":[218],"library.":[219],"observed":[221],"competitive":[224],"times":[227],"superior":[228],"practical":[231],"cases.":[232],"advantage":[234],"presented":[237],"methodology":[238],"lies":[239],"achieving":[241],"results":[243],"portable":[246],"manner":[247],"across":[248],"storage":[250],"formats":[251],"GPU":[253],"hardware":[254],"architecture":[255],"platforms.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}