{"id":"https://openalex.org/W7125957409","doi":"https://doi.org/10.1145/3774934.3786446","title":"A Diagonal Block Memory-Aware Polynomial Preconditioner for Linear and Eigenvalue Solvers","display_name":"A Diagonal Block Memory-Aware Polynomial Preconditioner for Linear and Eigenvalue Solvers","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125957409","doi":"https://doi.org/10.1145/3774934.3786446"},"language":null,"primary_location":{"id":"doi:10.1145/3774934.3786446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","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/A5124127570","display_name":"Xiaojian Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojian Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124138445","display_name":"Yuhui Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhui Ni","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102221431","display_name":"Fan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yuan","raw_affiliation_strings":["Xiangtan University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Xiangtan University, Changsha, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124116904","display_name":"Shengguo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengguo Li","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006729432","display_name":"Dezun Dong","orcid":"https://orcid.org/0000-0001-6243-8479"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezun Dong","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122922443","display_name":"Chuanfu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfu Xu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101816350","display_name":"Haipeng Jia","orcid":"https://orcid.org/0000-0002-9855-5367"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haipeng Jia","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124130365","display_name":"Jie Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5124127570"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27781597,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"660","last_page":"673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.4049000144004822,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.4049000144004822,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3637000024318695,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.05689999833703041,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.7434999942779541},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.5964999794960022},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.572700023651123},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5476999878883362},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4984999895095825},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.48820000886917114},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.46309998631477356},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4537999927997589}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.7434999942779541},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.572700023651123},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.48820000886917114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4869000017642975},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39719998836517334},{"id":"https://openalex.org/C85817219","wikidata":"https://www.wikidata.org/wiki/Q884772","display_name":"Block matrix","level":3,"score":0.3873000144958496},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.34540000557899475},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C169756996","wikidata":"https://www.wikidata.org/wiki/Q194919","display_name":"Eigendecomposition of a matrix","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C113313756","wikidata":"https://www.wikidata.org/wiki/Q332791","display_name":"Diagonal matrix","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C51647924","wikidata":"https://www.wikidata.org/wiki/Q1755277","display_name":"Tridiagonal matrix","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C101044782","wikidata":"https://www.wikidata.org/wiki/Q6787887","display_name":"Matrix polynomial","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C126352355","wikidata":"https://www.wikidata.org/wiki/Q2562273","display_name":"Polynomial matrix","level":4,"score":0.2554999887943268},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774934.3786446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","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":57,"referenced_works":["https://openalex.org/W993511226","https://openalex.org/W1506342804","https://openalex.org/W1512732958","https://openalex.org/W1525132831","https://openalex.org/W1538076361","https://openalex.org/W1590523881","https://openalex.org/W1621069953","https://openalex.org/W1961751213","https://openalex.org/W1964987772","https://openalex.org/W1987840949","https://openalex.org/W1990373616","https://openalex.org/W1990832096","https://openalex.org/W2002555321","https://openalex.org/W2004951603","https://openalex.org/W2009654791","https://openalex.org/W2011655084","https://openalex.org/W2029108714","https://openalex.org/W2029830594","https://openalex.org/W2035080386","https://openalex.org/W2041792040","https://openalex.org/W2047344035","https://openalex.org/W2060283640","https://openalex.org/W2070232376","https://openalex.org/W2074976694","https://openalex.org/W2095258827","https://openalex.org/W2099611016","https://openalex.org/W2100315046","https://openalex.org/W2105745683","https://openalex.org/W2111784516","https://openalex.org/W2116808829","https://openalex.org/W2138388932","https://openalex.org/W2142184646","https://openalex.org/W2145194992","https://openalex.org/W2165439482","https://openalex.org/W2208779871","https://openalex.org/W2234212075","https://openalex.org/W2469975815","https://openalex.org/W2480854438","https://openalex.org/W2751387202","https://openalex.org/W2914516353","https://openalex.org/W2957142384","https://openalex.org/W2962736137","https://openalex.org/W2963530710","https://openalex.org/W2967701142","https://openalex.org/W3119186146","https://openalex.org/W3175189837","https://openalex.org/W4205471980","https://openalex.org/W4300666158","https://openalex.org/W4312191554","https://openalex.org/W4312258136","https://openalex.org/W4381328331","https://openalex.org/W4384705388","https://openalex.org/W4388661983","https://openalex.org/W4392449925","https://openalex.org/W4402890182","https://openalex.org/W4411487111","https://openalex.org/W4413411841"],"related_works":[],"abstract_inverted_index":{"Krylov":[0],"subspace":[1],"methods":[2],"are":[3],"widely":[4],"used":[5],"in":[6,30,123],"scientific":[7],"computing":[8],"to":[9,36,85,106],"solve":[10],"large":[11],"sparse":[12],"linear":[13,110],"systems":[14,111],"and":[15,50,61,71,80,92,112,133],"eigenvalue":[16,113],"problems.":[17],"Their":[18],"performance":[19,101],"bottleneck":[20],"is":[21],"often":[22],"dominated":[23],"by":[24,102],"high-order":[25],"matrix-power":[26],"kernels":[27],"(MPK),":[28],"especially":[29],"polynomial":[31,107],"preconditioners":[32,108],"that":[33,53,97],"must":[34],"scale":[35],"millions":[37],"or":[38],"billions":[39],"of":[40,120],"variables.":[41],"We":[42],"present":[43],"Diagonal":[44],"Block":[45],"MPK":[46,100],"(DBMPK),":[47],"a":[48],"lightweight":[49],"parallel-friendly":[51],"optimization":[52],"partitions":[54],"the":[55],"input":[56],"matrix":[57],"into":[58],"diagonal":[59],"blocks":[60],"off-diagonal":[62],"regions.":[63],"This":[64],"design":[65],"enables":[66],"efficient":[67],"intra-block":[68],"data":[69],"reuse":[70],"eliminates":[72],"inter-block":[73],"dependencies.":[74],"It":[75],"improves":[76,99],"cache":[77],"locality,":[78],"parallelism,":[79],"reduces":[81],"preprocessing":[82],"overheads,":[83],"compared":[84],"existing":[86],"techniques.":[87],"Our":[88],"evaluation":[89],"on":[90,127],"x86":[91],"Arm":[93],"HPC":[94],"platforms":[95],"shows":[96],"DBMPK":[98],"26.6%-38.4%.":[103],"When":[104],"applied":[105],"for":[109],"problems,":[114],"it":[115],"achieves":[116],"consistent":[117],"end-to-end":[118],"speedups":[119],"18.6%-34.0%,":[121],"including":[122],"weak":[124],"scaling":[125],"tests":[126],"128":[128],"nodes,":[129],"demonstrating":[130],"strong":[131],"scalability":[132],"practical":[134],"impact.":[135]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-29T00:00:00"}