{"id":"https://openalex.org/W2903556862","doi":"https://doi.org/10.1109/hpec.2018.8547576","title":"Optimizing GPU Kernels for Irregular Batch Workloads: A Case Study for Cholesky Factorization","display_name":"Optimizing GPU Kernels for Irregular Batch Workloads: A Case Study for Cholesky Factorization","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2903556862","doi":"https://doi.org/10.1109/hpec.2018.8547576","mag":"2903556862"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2018.8547576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2018.8547576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE High Performance extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077268543","display_name":"Ahmad Abdelfattah","orcid":"https://orcid.org/0000-0001-5054-4784"},"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 Abdelfattah","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, USA","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","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":false,"raw_author_name":"Azzam Haidar","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, 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":["Innovative Computing Laboratory, University of Tennessee, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, 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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["Innovative Computing Laboratory, University of Tennessee, Knoxville, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innovative Computing Laboratory, University of Tennessee, Knoxville, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14619337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"9137","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9968000054359436,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8491888046264648},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.8357893824577332},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.8033661246299744},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7502719759941101},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7214100360870361},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6354714632034302},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.35286179184913635},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1525728702545166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8491888046264648},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.8357893824577332},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.8033661246299744},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7502719759941101},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7214100360870361},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6354714632034302},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35286179184913635},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1525728702545166},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2018.8547576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2018.8547576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE High Performance extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W44492739","https://openalex.org/W1028753842","https://openalex.org/W1737435842","https://openalex.org/W1985691044","https://openalex.org/W1997033059","https://openalex.org/W2006682733","https://openalex.org/W2018419001","https://openalex.org/W2123969616","https://openalex.org/W2127906479","https://openalex.org/W2138215414","https://openalex.org/W2162322364","https://openalex.org/W2183156981","https://openalex.org/W2199814763","https://openalex.org/W2268122618","https://openalex.org/W2410272182","https://openalex.org/W2444544770","https://openalex.org/W2471966094","https://openalex.org/W2499931820","https://openalex.org/W2531348778","https://openalex.org/W2580907809","https://openalex.org/W2588282852","https://openalex.org/W2617819327","https://openalex.org/W2736056409","https://openalex.org/W2751100001","https://openalex.org/W2767612671","https://openalex.org/W2793643991","https://openalex.org/W2887740241","https://openalex.org/W2966371448","https://openalex.org/W3101321165","https://openalex.org/W6626764175","https://openalex.org/W6693808235","https://openalex.org/W6723773145","https://openalex.org/W6741266834","https://openalex.org/W6767234692"],"related_works":["https://openalex.org/W2403987929","https://openalex.org/W2039814159","https://openalex.org/W2374847384","https://openalex.org/W2063512590","https://openalex.org/W2058965144","https://openalex.org/W2107649022","https://openalex.org/W2356488190","https://openalex.org/W2164382479","https://openalex.org/W2966537581","https://openalex.org/W2079508979"],"abstract_inverted_index":{"This":[0],"paper":[1,39],"introduces":[2],"several":[3],"frameworks":[4],"for":[5],"the":[6,47,61,78,81,91],"design":[7,70,89],"and":[8,35,60,80],"implementation":[9],"of":[10,44,83],"high":[11],"performance":[12],"GPU":[13],"kernels":[14],"that":[15],"target":[16],"batch":[17],"workloads":[18,23],"with":[19,74],"irregular":[20],"sizes.":[21],"Such":[22],"are":[24,72],"ubiquitous":[25],"in":[26,100],"many":[27],"scientific":[28],"applications,":[29],"including":[30],"sparse":[31],"direct":[32],"solvers,":[33],"astrophysics,":[34],"quantum":[36],"chemistry.":[37],"The":[38,54],"addresses":[40],"two":[41],"main":[42],"categories":[43],"frameworks,":[45],"taking":[46],"Cholesky":[48],"factorization":[49],"as":[50],"a":[51,104],"case":[52],"study.":[53],"first":[55],"uses":[56,63],"host-side":[57],"kernel":[58],"launches,":[59],"second":[62],"device-side":[64],"launches.":[65],"Within":[66],"each":[67,84],"category,":[68],"different":[69],"options":[71],"introduced,":[73],"an":[75],"emphasis":[76],"on":[77,103],"advantages":[79],"disadvantages":[82],"approach.":[85],"Our":[86],"best":[87],"performing":[88],"outperforms":[90],"state-of-the-art":[92],"CPU":[93],"implementation,":[94],"scoring":[95],"up":[96],"to":[97],"4.7\u00d7":[98],"speedup":[99],"double":[101],"precision":[102],"Pascal":[105],"P100":[106],"GPU.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}