{"id":"https://openalex.org/W4416199210","doi":"https://doi.org/10.1145/3712285.3759792","title":"Caracal: A GPU-Resident Sparse LU Solver with Lightweight Fine-Grained Scheduling","display_name":"Caracal: A GPU-Resident Sparse LU Solver with Lightweight Fine-Grained Scheduling","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199210","doi":"https://doi.org/10.1145/3712285.3759792"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759792","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759792","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077292051","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0003-3332-2092"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Jie Ren","raw_affiliation_strings":["Computer Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-3332-2092","affiliations":[{"raw_affiliation_string":"Computer Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032438787","display_name":"Tingxuan Zhong","orcid":"https://orcid.org/0009-0000-5086-4649"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Tingxuan Zhong","raw_affiliation_strings":["Computer Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0009-0000-5086-4649","affiliations":[{"raw_affiliation_string":"Computer Science, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046043219","display_name":"Yuxi Hong","orcid":"https://orcid.org/0000-0002-0741-6602"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxi Hong","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, USA"],"raw_orcid":"https://orcid.org/0000-0002-0741-6602","affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136077","display_name":"Guofeng Feng","orcid":"https://orcid.org/0009-0006-6107-2501"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guofeng Feng","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6107-2501","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xincheng Wang","orcid":"https://orcid.org/0009-0003-7753-6663"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xincheng Wang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-7753-6663","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648065","display_name":"Weile Jia","orcid":"https://orcid.org/0000-0001-8539-8326"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weile Jia","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8539-8326","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017526753","display_name":"Hatem Ltaief","orcid":"https://orcid.org/0000-0002-6897-1095"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Hatem Ltaief","raw_affiliation_strings":["Applied Mathematics and Computational Sciences, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-6897-1095","affiliations":[{"raw_affiliation_string":"Applied Mathematics and Computational Sciences, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283893","display_name":"David E. Keyes","orcid":"https://orcid.org/0000-0002-4052-7224"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"David Elliot Keyes","raw_affiliation_strings":["Applied Mathematics and Computational Sciences, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4052-7224","affiliations":[{"raw_affiliation_string":"Applied Mathematics and Computational Sciences, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1477","last_page":"1494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9581000208854675,"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":0.9581000208854675,"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":0.00570000009611249,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/speedup","display_name":"Speedup","score":0.9710000157356262},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6984999775886536},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6172000169754028},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.47130000591278076},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.459199994802475},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44920000433921814},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.38760000467300415},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.3849000036716461}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9710000157356262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707000017166138},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7825000286102295},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6984999775886536},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6172000169754028},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.47130000591278076},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44920000433921814},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3849000036716461},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759792","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759792","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1143651532","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W625657276","https://openalex.org/W1502558273","https://openalex.org/W1520511539","https://openalex.org/W1583920484","https://openalex.org/W1969154824","https://openalex.org/W1998894100","https://openalex.org/W2011832776","https://openalex.org/W2013424510","https://openalex.org/W2014730252","https://openalex.org/W2017509788","https://openalex.org/W2021108117","https://openalex.org/W2031218182","https://openalex.org/W2041999884","https://openalex.org/W2051917325","https://openalex.org/W2052602889","https://openalex.org/W2055094346","https://openalex.org/W2063675347","https://openalex.org/W2074093855","https://openalex.org/W2082222857","https://openalex.org/W2118076222","https://openalex.org/W2130886743","https://openalex.org/W2134066908","https://openalex.org/W2167255550","https://openalex.org/W2167797964","https://openalex.org/W2200391835","https://openalex.org/W2887905332","https://openalex.org/W2952013349","https://openalex.org/W3046854760","https://openalex.org/W3187688612","https://openalex.org/W3212893044","https://openalex.org/W4312949343","https://openalex.org/W4386764095","https://openalex.org/W4388662066","https://openalex.org/W4401861724","https://openalex.org/W4405754839"],"related_works":[],"abstract_inverted_index":{"We":[0],"address":[1],"inefficiencies":[2],"in":[3,10,54],"task":[4],"scheduling,":[5],"memory":[6,42,65],"management,":[7],"and":[8,77,121],"scalability":[9],"GPU-resident":[11],"sparse":[12],"LU":[13],"factorization":[14],"with":[15,29,110],"a":[16,30,63,73,87],"two-level":[17],"approach":[18],"of":[19,90,136],"sequentially":[20],"scheduled":[21],"coarse-grained":[22,127],"blocks":[23,27],"containing":[24],"multiple":[25],"fine-grained":[26,47],"managed":[28],"lightweight":[31],"static":[32],"scheduler":[33],"enabling":[34],"multi-stream":[35],"parallelism.":[36],"Additionally,":[37],"we":[38,61],"design":[39,66,85],"an":[40],"intelligent":[41],"caching":[43],"mechanism":[44],"for":[45],"the":[46,69,107,137],"scheduler,":[48],"which":[49],"retains":[50],"frequently":[51],"accessed":[52],"data":[53],"GPU":[55],"memory.":[56],"To":[57],"further":[58],"enhance":[59],"scalability,":[60],"introduce":[62],"distributed":[64],"that":[67],"partitions":[68],"input":[70],"matrix":[71],"using":[72],"1D":[74],"block-cyclic":[75],"distribution":[76],"optimizes":[78],"inter-GPU":[79],"communication":[80],"via":[81],"NVLink.":[82],"The":[83],"multi-GPU":[84],"reaches":[86],"computational":[88],"throughput":[89],"6.46":[91],"TFLOP/s":[92],"on":[93],"four":[94],"A100":[95],"GPUs,":[96],"demonstrating":[97],"promising":[98],"scalability.":[99],"This":[100],"is":[101],"up":[102,133],"to":[103,134],"7x":[104],"speedup":[105,114,118,123],"over":[106,115,119,124],"latest":[108],"SuperLU_DIST":[109],"3D":[111],"communication,":[112],"94x":[113],"PanguLU,":[116],"16x":[117],"PasTiX,":[120],"10x":[122],"our":[125],"own":[126],"dynamic":[128],"scheduling":[129],"implementation":[130],"while":[131],"reaching":[132],"21%":[135],"A100\u2019s":[138],"theoretical":[139],"peak":[140],"performance.":[141]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-12T00:00:00"}