{"id":"https://openalex.org/W4411616705","doi":"https://doi.org/10.1177/10943420251347460","title":"Efficient solution of batched band linear systems on GPUs","display_name":"Efficient solution of batched band linear systems on GPUs","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4411616705","doi":"https://doi.org/10.1177/10943420251347460"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251347460","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251347460","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/10943420251347460","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059984998","display_name":"Pratik Nayak","orcid":"https://orcid.org/0000-0002-7961-1159"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]},{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Pratik Nayak","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany","Technical University of Munich, Heilbronn, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7961-1159","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Technical University of Munich, Heilbronn, Germany","institution_ids":["https://openalex.org/I41121874","https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056818834","display_name":"Isha Aggarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Isha Aggarwal","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012133869","display_name":"Hartwig Anzt","orcid":"https://orcid.org/0000-0003-2177-952X"},"institutions":[{"id":"https://openalex.org/I41121874","display_name":"Heilbronn University","ror":"https://ror.org/04g5gcg95","country_code":"DE","type":"education","lineage":["https://openalex.org/I41121874"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"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":["DE","US"],"is_corresponding":false,"raw_author_name":"Hartwig Anzt","raw_affiliation_strings":["ICL, University of Tennessee, Knoxville, TN, USA","Technical University of Munich, Heilbronn, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2177-952X","affiliations":[{"raw_affiliation_string":"ICL, University of Tennessee, Knoxville, TN, USA","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"Technical University of Munich, Heilbronn, Germany","institution_ids":["https://openalex.org/I41121874","https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059984998"],"corresponding_institution_ids":["https://openalex.org/I102335020","https://openalex.org/I41121874","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13650442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"5","first_page":"615","last_page":"630"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9991000294685364,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9941999912261963,"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":0.4587022066116333},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4152730107307434},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4046165943145752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4587022066116333},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4152730107307434},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4046165943145752}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420251347460","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251347460","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/10943420251347460","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251347460","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3961431766","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320337480","funder_display_name":"Basic Energy Sciences"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320337480","display_name":"Basic Energy Sciences","ror":"https://ror.org/05mg91w61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W36826159","https://openalex.org/W1520511539","https://openalex.org/W2052602889","https://openalex.org/W2065360261","https://openalex.org/W2078794610","https://openalex.org/W2141331848","https://openalex.org/W2161456019","https://openalex.org/W2166751342","https://openalex.org/W2340769696","https://openalex.org/W2341288466","https://openalex.org/W2622428623","https://openalex.org/W2733255940","https://openalex.org/W2806238950","https://openalex.org/W2883920724","https://openalex.org/W2888823183","https://openalex.org/W3038558128","https://openalex.org/W3139401450","https://openalex.org/W3145384893","https://openalex.org/W3204062674","https://openalex.org/W4200591469","https://openalex.org/W4285609454","https://openalex.org/W4364355656","https://openalex.org/W4388581158","https://openalex.org/W6911338274","https://openalex.org/W6950508221"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"direct":[1,29],"solution":[2,30],"of":[3,5,31,57,77,111,155,168,205],"batches":[4],"band":[6,37,55,68,208],"linear":[7,32],"systems":[8],"in":[9,63],"parallel":[10],"is":[11],"important":[12],"for":[13,26,42,87,137,144,210,221],"many":[14],"applications.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19,113],"elaborate":[20],"on":[21,131,196,238],"three":[22,43],"new":[23],"GPU":[24,183],"algorithms":[25,41,136],"the":[27,54,58,74,78,103,142,166,172,181,188,203,223,263,266],"data-parallel":[28],"system":[33],"batches,":[34],"sharing":[35],"a":[36,84,108,115,153,215,228],"structure.":[38],"We":[39,52,82,133,164,200,232],"develop":[40,83],"matrix":[44,69,146],"types:":[45],"tridiagonal,":[46],"small":[47],"bandwidth,":[48],"and":[49,60,71,118,140,151,178,186,249,265],"wide":[50],"bandwidth.":[51],"exploit":[53],"structure":[56],"matrix,":[59],"store":[61],"it":[62],"an":[64],"efficient":[65],"fashion":[66],"(LAPACK":[67],"format)":[70],"ensure":[72,91,107],"that":[73,234],"SIMD":[75],"parallelism":[76],"GPUs":[79,139],"are":[80,237],"maximized.":[81],"panel-based":[85],"factorization":[86],"wide-band":[88],"matrices":[89,211],"to":[90,106,123,149,247,251,259],"coalesced":[92],"access":[93],"(with":[94],"column-major":[95],"storage)":[96],"while":[97],"minimizing":[98],"main":[99],"memory":[100],"traffic.":[101],"For":[102],"tridiagonal":[104,256],"solvers,":[105,245,257],"high":[109],"level":[110],"concurrency,":[112],"adapt":[114],"divide-and-conquer":[116],"approach":[117],"utilize":[119],"co-operative":[120],"group":[121],"functionality":[122],"efficiently":[124],"communicate":[125],"between":[126],"compute":[127],"units":[128],"(in":[129],"registers)":[130],"GPUs.":[132],"implement":[134],"these":[135],"NVIDIA":[138],"study":[141],"performance":[143,167],"varying":[145],"sizes":[147],"(16":[148],"1024)":[150],"across":[152],"range":[154],"batch":[156],"items":[157],"(upto":[158],"1":[159],"\u00d7":[160],"10":[161],"6":[162],").":[163],"compare":[165],"our":[169,206,235],"implementations":[170,176,236],"with":[171,180,187],"corresponding":[173],"optimized":[174,189,220],"vendor":[175,267],"(cuSPARSE":[177],"MKL),":[179],"state-of-the-art":[182,264],"library":[184],"MAGMA,":[185],"LAPACK":[190],"implementation":[191],"provided":[192,268],"by":[193],"Intel":[194,197],"MKL":[195],"Skylake":[198],"CPUs.":[199],"also":[201],"showcase":[202],"effectiveness":[204],"batched":[207,243,255],"solvers":[209],"originating":[212],"from":[213],"XGC,":[214],"gyrokinetic":[216],"Particle-In-Cell":[217],"(PIC)":[218],"application":[219],"modeling":[222],"edge":[224],"region":[225],"plasma":[226,229],"within":[227],"physics":[230],"application.":[231],"show":[233],"average":[239],"\u223c":[240,252],"2\u00d7":[241],"(for":[242,254],"banded":[244],"compared":[246,258],"MAGMA":[248],"MKL)":[250],"3\u00d7":[253],"cuSPARSE)":[260],"faster":[261],"than":[262],"implementations.":[269]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}