{"id":"https://openalex.org/W7125605801","doi":"https://doi.org/10.1145/3774949.3774967","title":"Optimization of Sparse Matrix Block LU Factorization: A Hybrid MPI-OpenMP Parallel Method","display_name":"Optimization of Sparse Matrix Block LU Factorization: A Hybrid MPI-OpenMP Parallel Method","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W7125605801","doi":"https://doi.org/10.1145/3774949.3774967"},"language":null,"primary_location":{"id":"doi:10.1145/3774949.3774967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774949.3774967","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 2025 9th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774949.3774967","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104582208","display_name":"Yujiao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujiao Han","raw_affiliation_strings":["Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0009-8237-3882","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingshan Pan","orcid":"https://orcid.org/0009-0007-5792-6516"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingshan Pan","raw_affiliation_strings":["Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0007-5792-6516","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123767657","display_name":"Min Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Tian","raw_affiliation_strings":["Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0000-9930-4802","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113115928","display_name":"Jiwei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwei Xu","raw_affiliation_strings":["Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0003-8256-2452","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123755534","display_name":"Lu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China"],"raw_orcid":"https://orcid.org/0009-0001-2133-4830","affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center, Qilu University of Technology, Jinan, Shandong, China","institution_ids":["https://openalex.org/I152269853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I152269853"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58485692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.42089998722076416,"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":0.42089998722076416,"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":0.3774999976158142,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.0908999964594841,"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/scalability","display_name":"Scalability","score":0.6848000288009644},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6547999978065491},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6452000141143799},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6220999956130981},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.6211000084877014},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5412999987602234},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4880000054836273},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.454800009727478},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.44679999351501465}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081999778747559},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6848000288009644},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.659600019454956},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6547999978065491},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6452000141143799},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.6211000084877014},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5105000138282776},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4880000054836273},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C54219892","wikidata":"https://www.wikidata.org/wiki/Q4080929","display_name":"Matrix-free methods","level":4,"score":0.36890000104904175},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C11644782","wikidata":"https://www.wikidata.org/wiki/Q15401790","display_name":"Cost efficiency","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C2778258933","wikidata":"https://www.wikidata.org/wiki/Q16918986","display_name":"Decomposition method (queueing theory)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774949.3774967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774949.3774967","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 2025 9th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774949.3774967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774949.3774967","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 2025 9th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1989396323","https://openalex.org/W2002991695","https://openalex.org/W2061397794","https://openalex.org/W2496831976","https://openalex.org/W3186155333"],"related_works":[],"abstract_inverted_index":{"The":[0,120],"solution":[1,127,131],"of":[2,21,58,114,132],"sparse":[3,41,133],"linear":[4,134],"systems":[5],"plays":[6],"a":[7,111,117],"crucial":[8],"role":[9],"in":[10,62],"scientific":[11],"computing":[12,64],"and":[13,27,73,80,90,103,125],"engineering":[14],"applications,":[15],"with":[16,77,136],"LU":[17,44,60],"decomposition":[18,45,61],"being":[19],"one":[20],"the":[22,48,56,84,97,129],"core":[23],"algorithms.":[24],"Its":[25],"efficiency":[26,89],"scalability":[28,102],"directly":[29],"impact":[30],"overall":[31],"computational":[32,88,104],"performance.":[33,92],"This":[34],"paper":[35],"proposes":[36],"an":[37,123],"optimized":[38],"algorithm":[39,85,99],"for":[40,116,128],"matrix":[42,71,108],"block":[43,69],"based":[46],"on":[47],"MPI-OpenMP":[49],"hybrid":[50],"parallel":[51,91,130],"approach,":[52],"aiming":[53],"to":[54],"address":[55],"bottlenecks":[57],"traditional":[59],"high-performance":[63],"environments.":[65],"By":[66],"dynamically":[67],"adjusting":[68],"sizes,":[70,109],"scaling,":[72],"pivot":[74],"perturbation,":[75],"combined":[76],"OpenMP":[78],"parallelization":[79],"manual":[81],"loop":[82],"unrolling,":[83],"significantly":[86],"enhances":[87],"Experimental":[93],"results":[94],"show":[95],"that":[96],"proposed":[98],"demonstrates":[100],"excellent":[101],"performance":[105],"across":[106],"various":[107],"achieving":[110],"speedup":[112],"ratio":[113],"4.11":[115],"1250\u00d71250":[118],"matrix.":[119],"study":[121],"provides":[122],"efficient":[124],"scalable":[126],"systems,":[135],"broad":[137],"application":[138],"potential.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-25T00:00:00"}