{"id":"https://openalex.org/W7160853528","doi":"https://doi.org/10.1145/3815589","title":"BLR-Krylov: A Single-GPU Iterative SpMM Framework with Communication Avoidance and Block Low-Rank Optimization","display_name":"BLR-Krylov: A Single-GPU Iterative SpMM Framework with Communication Avoidance and Block Low-Rank Optimization","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160853528","doi":"https://doi.org/10.1145/3815589"},"language":"en","primary_location":{"id":"doi:10.1145/3815589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815589","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3815589","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100524718","display_name":"Li Wen","orcid":"https://orcid.org/0009-0005-9531-5500"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Li","raw_affiliation_strings":["College of Artificial Intelligence and Software Engineering, Nanyang Normal University"],"raw_orcid":"https://orcid.org/0000-0002-6024-9698","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Software Engineering, Nanyang Normal University","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135866108","display_name":"Zh\u00e8ng Zh\u0101ng","orcid":"https://orcid.org/0009-0000-1683-3267"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["College of Artificial Intelligence and Software Engineering, Nanyang Normal University"],"raw_orcid":"https://orcid.org/0009-0000-1683-3267","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Software Engineering, Nanyang Normal University","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123879833","display_name":"Jie Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["College of Artificial Intelligence and Software Engineering, Nanyang Normal University"],"raw_orcid":"https://orcid.org/0009-0008-8731-1552","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Software Engineering, Nanyang Normal University","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135862228","display_name":"Song Zhu","orcid":"https://orcid.org/0009-0005-6570-8872"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Zhu","raw_affiliation_strings":["College of Artificial Intelligence and Software Engineering, Nanyang Normal University"],"raw_orcid":"https://orcid.org/0009-0005-6570-8872","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Software Engineering, Nanyang Normal University","institution_ids":["https://openalex.org/I4210110718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025273110","display_name":"Ming Hui","orcid":"https://orcid.org/0000-0003-2915-8656"},"institutions":[{"id":"https://openalex.org/I4210110718","display_name":"Nanyang Normal University","ror":"https://ror.org/01f7yer47","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210110718"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Hui","raw_affiliation_strings":["College of Artificial Intelligence and Software Engineering, Nanyang Normal University"],"raw_orcid":"https://orcid.org/0000-0003-2915-8656","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Software Engineering, Nanyang Normal University","institution_ids":["https://openalex.org/I4210110718"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210110718"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57462537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.5691999793052673,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.5691999793052673,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.1421000063419342,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.04490000009536743,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/krylov-subspace","display_name":"Krylov subspace","score":0.7659000158309937},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5817999839782715},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.5440999865531921},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.46129998564720154},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45260000228881836},{"id":"https://openalex.org/keywords/matrix-free-methods","display_name":"Matrix-free methods","score":0.45170000195503235},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.44130000472068787},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.40119999647140503},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.39070001244544983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075000047683716},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.7659000158309937},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5817999839782715},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4860999882221222},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C54219892","wikidata":"https://www.wikidata.org/wiki/Q4080929","display_name":"Matrix-free methods","level":4,"score":0.45170000195503235},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.44130000472068787},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.39070001244544983},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2777561913","wikidata":"https://www.wikidata.org/wiki/Q19599527","display_name":"Power integrity","level":4,"score":0.2962000072002411},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2800000011920929},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3815589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815589","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3815589","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815589","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W1547507450","https://openalex.org/W1559275088","https://openalex.org/W1575701986","https://openalex.org/W1984840642","https://openalex.org/W2035080386","https://openalex.org/W2043502750","https://openalex.org/W2050576295","https://openalex.org/W2052440657","https://openalex.org/W2065607954","https://openalex.org/W2089437293","https://openalex.org/W2097897435","https://openalex.org/W2116341502","https://openalex.org/W2140153041","https://openalex.org/W2316564661","https://openalex.org/W2733888264","https://openalex.org/W2900806478","https://openalex.org/W4244063180"],"related_works":[],"abstract_inverted_index":{"Sparse":[0,73],"General":[1],"Matrix":[2],"Multiplication":[3],"(SpMM)":[4],"is":[5,171],"a":[6,70,131],"fundamental":[7],"kernel":[8],"in":[9,138],"iterative":[10,21,59,139],"scientific":[11],"computing":[12],"and":[13,40,98,148],"graph":[14],"neural":[15],"network":[16],"inference.":[17],"On":[18],"single-GPU":[19],"platforms,":[20],"SpMM":[22,60],"suffers":[23],"from":[24],"two":[25],"major":[26],"performance":[27],"bottlenecks:":[28],"excessive":[29],"memory":[30,117,143],"traffic":[31],"caused":[32],"by":[33],"repeated":[34],"loading":[35],"of":[36],"Krylov":[37,66,110],"basis":[38,92,112],"vectors,":[39,113],"low":[41],"computational":[42],"efficiency":[43],"due":[44],"to":[45,95,108,146,153],"irregular":[46],"sparsity":[47],"patterns.":[48],"To":[49,165],"address":[50],"these":[51],"challenges,":[52],"this":[53],"article":[54],"proposes":[55],"BLR-Krylov":[56,77,129],",":[57],"an":[58],"optimization":[61],"framework":[62],"that":[63,128],"integrates":[64],"Communication-Avoiding":[65],"(CA-Krylov)":[67],"methods":[68],"with":[69],"Block":[71],"Low-Rank":[72],"(BLR-Sparse)":[74],"matrix":[75,105],"format.":[76],"first":[78],"preprocesses":[79],"sparse":[80],"matrices":[81],"into":[82],"the":[83],"BLR-Sparse":[84],"format,":[85],"where":[86],"low-rank":[87],"blocks":[88],"are":[89],"compressed":[90],"through":[91],"vector":[93],"decomposition":[94],"reduce":[96],"storage":[97],"arithmetic":[99],"overhead.":[100],"It":[101],"then":[102],"employs":[103],"GPU-optimized":[104],"power":[106],"kernels":[107],"batch-compute":[109],"subspace":[111],"effectively":[114],"minimizing":[115],"global":[116,142],"accesses":[118],"across":[119],"iterations.":[120],"Experimental":[121],"results":[122],"on":[123],"multiple":[124],"GPU":[125],"architectures":[126],"demonstrate":[127],"achieves":[130],"4.0\u20136.0\u00d7":[132],"speedup":[133],"over":[134],"existing":[135],"communication-avoiding":[136],"approaches":[137],"workloads,":[140],"increases":[141],"bandwidth":[144],"utilization":[145,152],"82%\u201387%,":[147],"improves":[149],"tensor":[150],"core":[151],"85%\u201392%,":[154],"while":[155],"maintaining":[156],"numerical":[157],"accuracy":[158],"within":[159],"1":[160],"\u00d7":[161],"10":[162],"-6":[163],".":[164],"facilitate":[166],"reproducibility,":[167],"partial":[168],"source":[169],"code":[170],"publicly":[172],"available":[173],"at":[174],"https://github.com/19547035579zz-tech/BLR-Krylov.":[175]},"counts_by_year":[],"updated_date":"2026-06-28T06:15:30.350997","created_date":"2026-05-12T00:00:00"}