{"id":"https://openalex.org/W4414198918","doi":"https://doi.org/10.1109/dac63849.2025.11133082","title":"Me-MPK: Accelerating Krylov Subspace Solvers via Memory-efficient Matrix-Power Kernel","display_name":"Me-MPK: Accelerating Krylov Subspace Solvers via Memory-efficient Matrix-Power Kernel","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414198918","doi":"https://doi.org/10.1109/dac63849.2025.11133082"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","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/A5036679136","display_name":"Haozhong Qiu","orcid":"https://orcid.org/0009-0009-0434-8075"},"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":"Haozhong Qiu","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059351590","display_name":"Chuanfu Xu","orcid":"https://orcid.org/0000-0002-4876-2368"},"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,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083171604","display_name":"Jianbin Fang","orcid":"https://orcid.org/0000-0003-3542-4869"},"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":"Jianbin Fang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087730416","display_name":"Shengguo Li","orcid":"https://orcid.org/0000-0001-7827-6304"},"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,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023992845","display_name":"Liang Deng","orcid":"https://orcid.org/0000-0003-1444-4588"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Deng","raw_affiliation_strings":["China Aerodynamic Research and Development Center,Mianyang,China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamic Research and Development Center,Mianyang,China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409855","display_name":"Jian Zhang","orcid":"https://orcid.org/0000-0001-5418-0455"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhang","raw_affiliation_strings":["China Aerodynamic Research and Development Center,Mianyang,China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamic Research and Development Center,Mianyang,China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081447482","display_name":"Z. G. Dai","orcid":"https://orcid.org/0009-0008-0885-2845"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Dai","raw_affiliation_strings":["China Aerodynamic Research and Development Center,Mianyang,China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamic Research and Development Center,Mianyang,China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101827333","display_name":"Yue Ding","orcid":"https://orcid.org/0009-0009-1025-5238"},"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":"Yue Ding","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108085333","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-4258-9856"},"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":"Yue Wang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103686412","display_name":"Zhiping Han","orcid":"https://orcid.org/0009-0002-7605-9992"},"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":"Zhimeng Han","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008369819","display_name":"Yonggang Che","orcid":"https://orcid.org/0000-0001-6906-4940"},"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":"Yonggang Che","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454211","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"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,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5036679136"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.2383,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83090856,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9713000059127808,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11321","display_name":"Error Correcting Code Techniques","score":0.9699000120162964,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9463000297546387,"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/speedup","display_name":"Speedup","score":0.7943000197410583},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.7168999910354614},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6409000158309937},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5953999757766724},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5842999815940857},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4499000012874603},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79830002784729},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7943000197410583},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.7168999910354614},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6223999857902527},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5953999757766724},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4413999915122986},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.3257000148296356},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1575701986","https://openalex.org/W1590523881","https://openalex.org/W2035080386","https://openalex.org/W2070232376","https://openalex.org/W2126004407","https://openalex.org/W2140269398","https://openalex.org/W2165439482","https://openalex.org/W2234212075","https://openalex.org/W2480854438","https://openalex.org/W2570841452","https://openalex.org/W2610122093","https://openalex.org/W2957142384","https://openalex.org/W2983719957","https://openalex.org/W3146331811","https://openalex.org/W3166510811","https://openalex.org/W3205811905","https://openalex.org/W4312191554","https://openalex.org/W4384705388","https://openalex.org/W4391985182","https://openalex.org/W4405755653"],"related_works":[],"abstract_inverted_index":{"This":[0,118],"paper":[1,119],"focuses":[2],"on":[3,11,106,139,168,241],"optimizing":[4],"the":[5,20,73,82,186,227,255],"Matrix-Power":[6],"Kernel":[7],"(MPK),":[8],"which":[9,54,154],"relies":[10],"a":[12,26,47,121,146,151,176,203,248],"series":[13],"of":[14,29,130,197,235,258],"Sparse":[15],"Matrix-Vector":[16],"multiplications":[17],"(SpMVs)":[18],"using":[19],"same":[21],"sparse":[22,36,58,62,152,256],"matrix.":[23],"MPK":[24,45,138],"is":[25],"crucial":[27],"component":[28],"Krylov":[30,216],"subspace":[31,217],"methods":[32],"for":[33,49,76,137,150,194],"solving":[34],"large":[35],"linear":[37],"systems":[38],"in":[39,52,65,95,202,213,254],"various":[40],"fields,":[41],"including":[42],"circuit":[43],"simulations.":[44],"offers":[46],"potential":[48,157],"matrix":[50,83,108,135],"reuse":[51,109,133],"cache,":[53],"can":[55,93],"accelerate":[56],"memory-bound":[57],"solvers.":[59],"Additionally,":[60],"many":[61],"matrices":[63],"encountered":[64],"applications":[66],"are":[67,191],"symmetric,":[68],"allowing":[69],"us":[70],"to":[71,113,171,206,237,260],"reduce":[72],"memory":[74],"footprint":[75],"SpMVs":[77,92],"by":[78],"half.":[79],"However,":[80],"reusing":[81],"introduces":[84],"data":[85,96,158],"dependencies":[86,159,182],"between":[87],"subsequent":[88],"SpMVs,":[89],"and":[90,134,160,174,183,219,239,243,265],"symmetric":[91,200],"result":[94],"conflicts":[97,184],"during":[98],"shared-memory":[99,140],"parallelization.":[100],"Previous":[101],"research":[102],"has":[103],"often":[104],"focused":[105],"either":[107],"or":[110,199],"symmetry,":[111],"failing":[112],"leverage":[114],"both":[115,131],"aspects":[116],"effectively.":[117],"proposes":[120],"unified,":[122],"memory-efficient":[123],"approach":[124],"called":[125],"Me-MPK":[126,212,224],"that":[127,179,223],"takes":[128],"advantage":[129],"cache":[132,208],"symmetry":[136],"multi-core":[141],"systems.":[142],"We":[143,210],"first":[144],"introduce":[145],"unified":[147],"dependency":[148],"graph":[149,170],"matrix,":[153],"represents":[155],"all":[156,181],"conflicts.":[161],"Next,":[162],"we":[163,250],"perform":[164],"architecture-aware":[165],"recursive":[166],"partitioning":[167],"this":[169],"create":[172],"subgraphs":[173,190],"formulate":[175],"separating":[177],"subgraph":[178],"decouples":[180],"among":[185],"subgraphs.":[187],"These":[188],"independent":[189],"then":[192],"scheduled":[193],"parallel":[195],"execution":[196],"SpMV":[198,201],"specified":[204],"order":[205],"optimize":[207],"reuse.":[209],"apply":[211],"two":[214],"s-Step":[215],"solvers,":[218],"our":[220],"evaluations":[221],"show":[222],"significantly":[225],"outperforms":[226],"current":[228],"state-of-the-art":[229],"solutions,":[230],"delivering":[231],"an":[232],"average":[233],"speedup":[234,253],"up":[236,259],"2.00X":[238],"1.86X":[240],"X86":[242],"ARM":[244],"CPUs,":[245],"respectively.":[246],"As":[247],"result,":[249],"achieve":[251],"overall":[252],"solvers":[257],"$\\mathbf{1.":[261,266],"6":[262],"5":[263,267],"X}$":[264],"8":[268],"X}$.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
