{"id":"https://openalex.org/W4408049835","doi":"https://doi.org/10.1145/3710848.3710894","title":"Improving Tridiagonalization Performance on GPU Architectures","display_name":"Improving Tridiagonalization Performance on GPU Architectures","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408049835","doi":"https://doi.org/10.1145/3710848.3710894"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710894","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710894","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710894","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710894","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069210933","display_name":"Hansheng Wang","orcid":"https://orcid.org/0009-0006-0035-2323"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hansheng Wang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051676438","display_name":"Zhekai Duan","orcid":"https://orcid.org/0000-0002-0283-8419"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhekai Duan","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084729575","display_name":"Zitian Zhao","orcid":"https://orcid.org/0000-0001-8605-0938"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zitian Zhao","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Siqi Wu","orcid":"https://orcid.org/0009-0001-4459-4387"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Wu","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005437152","display_name":"Sulu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saiqi Zheng","raw_affiliation_strings":["Xi'an Jiaotong-Liverpool University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong-Liverpool University","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100393695","display_name":"Qiao Li","orcid":"https://orcid.org/0000-0002-4579-4268"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Li","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051642924","display_name":"Xu Jiang","orcid":"https://orcid.org/0000-0003-2675-2895"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Jiang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091290657","display_name":"Shaoshuai Zhang","orcid":"https://orcid.org/0000-0002-9525-1659"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoshuai Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5069210933"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":10.9914,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.98047117,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"469","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9984999895095825,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136918306350708},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49640709161758423}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136918306350708},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49640709161758423}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3710848.3710894","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710894","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710894","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3710848.3710894","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710894","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710894","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1525095662","display_name":null,"funder_award_id":"A1098531023601465","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5824520547","display_name":null,"funder_award_id":"CCF-GH OF 2024002","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408049835.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2072396164","https://openalex.org/W2073260424","https://openalex.org/W2104110430","https://openalex.org/W2119522963","https://openalex.org/W2122860281","https://openalex.org/W2148678374","https://openalex.org/W2164895445","https://openalex.org/W2208150243","https://openalex.org/W2308566534","https://openalex.org/W2765309601","https://openalex.org/W2887881931","https://openalex.org/W3002341896","https://openalex.org/W3007543653","https://openalex.org/W3039141850","https://openalex.org/W4292928781","https://openalex.org/W4321446155","https://openalex.org/W4324292875"],"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":{"Tridiagonalization,":[0],"which":[1,123],"is":[2,65,124],"a":[3,14,18,44,89],"key":[4],"step":[5],"in":[6,51],"symmetric":[7,15],"eigenvalue":[8],"decomposition":[9],"(EVD),":[10],"aims":[11],"to":[12,17,104,120],"convert":[13],"matrix":[16],"tridiagonal":[19],"form.":[20],"In":[21,70],"Nvidia's":[22],"cuSOLVER":[23],"library,":[24],"the":[25,48,52,62,75,78,106,112],"FP64":[26,114],"precision":[27,115],"tridiagonalization":[28,63,82,107,116],"process":[29],"only":[30],"reach":[31],"2.1":[32],"TFLOPs":[33,37,122],"out":[34],"of":[35,47,81,100],"67":[36],"on":[38,67,83],"H100":[39],"GPU,":[40],"and":[41,86,126,131],"it":[42],"consumes":[43],"significant":[45],"portion":[46],"elapsed":[49],"time":[50],"entire":[53],"EVD":[54],"process,":[55],"accounting":[56],"for":[57],"over":[58],"97%.":[59],"Thus,":[60],"improving":[61],"performance":[64,80],"crucial":[66],"accelerating":[68],"EVD.":[69],"this":[71],"paper,":[72],"we":[73,87],"analyze":[74],"reasons":[76],"behind":[77],"suboptimal":[79],"GPU":[84],"architectures,":[85],"propose":[88],"new":[90],"double":[91],"blocking":[92],"band":[93],"reduction":[94],"algorithm":[95],"along":[96],"with":[97],"an":[98],"implementation":[99],"GPU-based":[101],"bulge":[102],"chasing":[103],"improve":[105],"performance.":[108],"Through":[109],"experimental":[110],"evaluation,":[111],"proposed":[113],"method":[117],"yields":[118],"up":[119],"19.6":[121],"9.3x":[125],"5.2x":[127],"faster":[128],"compared":[129],"cuSOVLER":[130],"MAGMA,":[132],"respectively.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
