{"id":"https://openalex.org/W7125899626","doi":"https://doi.org/10.1109/smc58881.2025.11342682","title":"An Improved Distributed SpMV with Cache-Aware Optimization and Load Balancing","display_name":"An Improved Distributed SpMV with Cache-Aware Optimization and Load Balancing","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125899626","doi":"https://doi.org/10.1109/smc58881.2025.11342682"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5124118311","display_name":"Yunkun Shang","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"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunkun Shang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442406","display_name":"Yuan Zhuang","orcid":"https://orcid.org/0000-0001-8105-9319"},"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"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhuang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069233153","display_name":"Yunhui Zeng","orcid":"https://orcid.org/0000-0003-3398-6884"},"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"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhui Zeng","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan),Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68083376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4978","last_page":"4983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6007000207901001,"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":0.6007000207901001,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.09130000323057175,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.08720000088214874,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/load-balancing","display_name":"Load balancing (electrical power)","score":0.65420001745224},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4643999934196472},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4366999864578247},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3928999900817871},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.35269999504089355},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.35249999165534973},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.335999995470047},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.3357999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8765000104904175},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7109000086784363},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.65420001745224},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4643999934196472},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4366999864578247},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2779370713","wikidata":"https://www.wikidata.org/wiki/Q357554","display_name":"Load management","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27480000257492065},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.27379998564720154},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2028045344","https://openalex.org/W2035080386","https://openalex.org/W2088866486","https://openalex.org/W2115052535","https://openalex.org/W2891832717","https://openalex.org/W2964515976","https://openalex.org/W2971508019","https://openalex.org/W2979747168","https://openalex.org/W3126655641","https://openalex.org/W3139495005","https://openalex.org/W3176901945","https://openalex.org/W3202552726","https://openalex.org/W4223467872","https://openalex.org/W4236418138","https://openalex.org/W4312771767","https://openalex.org/W4383749629","https://openalex.org/W4385623033","https://openalex.org/W4400422163","https://openalex.org/W4400910447","https://openalex.org/W4401408866","https://openalex.org/W4408047721"],"related_works":[],"abstract_inverted_index":{"Sparse":[0,64],"Matrix-Vector":[1],"Multiplication":[2],"(SpMV)":[3],"is":[4,30],"a":[5,14,27,103],"critical":[6],"operation":[7],"in":[8,17],"scientific":[9],"and":[10,46,97,109,121,130,134,143,154,160,165],"high-performance":[11],"computing,":[12],"playing":[13],"key":[15],"role":[16],"large-scale":[18],"numerical":[19],"simulations.":[20],"Handling":[21],"extremely":[22],"large":[23,172],"sparse":[24,174],"matrices":[25],"on":[26,61,171],"single":[28],"node":[29],"challenging,":[31],"making":[32],"distributed":[33,39,58,104,136,148],"computing":[34],"an":[35],"effective":[36],"solution.":[37],"Existing":[38],"SpMV":[40,59,105,149],"optimizations":[41],"often":[42],"overlook":[43],"data":[44],"locality":[45],"suffer":[47],"from":[48],"communication":[49,98],"bottlenecks.":[50],"This":[51],"paper":[52],"proposes":[53],"two":[54],"optimization":[55],"strategies":[56,116],"for":[57],"based":[60],"the":[62,177],"Compressed":[63],"Row":[65],"(CSR)":[66],"format":[67],"to":[68,86,112,146],"improve":[69,117],"multi-node":[70,180],"efficiency.":[71],"First,":[72],"combining":[73],"cache-aware":[74],"memory":[75,93],"access":[76],"with":[77,138],"binary":[78],"search,":[79],"we":[80,101],"partition":[81],"thread":[82],"tasks":[83],"across":[84,119],"nodes":[85,120],"enable":[87],"fine-grained":[88],"non-zero":[89],"element":[90],"distribution,":[91],"reducing":[92],"conflicts,":[94],"load":[95,110],"imbalance,":[96],"overhead.":[99],"Second,":[100],"design":[102],"kernel":[106],"incorporating":[107],"vectorization":[108],"balancing":[111],"enhance":[113],"performance.":[114],"These":[115],"coordination":[118],"resource":[122],"utilization.":[123],"Experiments":[124],"show":[125],"average":[126,159],"speedups":[127,140,162],"of":[128,141,163,179],"81.82\u00d7":[129],"7.99\u00d7":[131],"over":[132],"classical":[133],"graph-partitioned":[135],"SpMV,":[137],"peak":[139,161],"462.34\u00d7":[142],"45.85\u00d7.":[144],"Compared":[145],"recent":[147],"algorithms":[150],"that":[151],"balance":[152],"computation":[153],"communication,":[155],"our":[156],"method":[157],"achieves":[158],"1.23\u00d7":[164],"4.27\u00d7.":[166],"The":[167],"algorithm":[168],"scales":[169],"well":[170],"irregular":[173],"matrices,":[175],"demonstrating":[176],"effectiveness":[178],"collaborative":[181],"optimization.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-29T00:00:00"}
