{"id":"https://openalex.org/W4411800106","doi":"https://doi.org/10.1109/ccgrid64434.2025.00053","title":"A Nonlinear Hash-Based Optimization Method for SpMV on GPUs","display_name":"A Nonlinear Hash-Based Optimization Method for SpMV on GPUs","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4411800106","doi":"https://doi.org/10.1109/ccgrid64434.2025.00053"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid64434.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104688800","display_name":"Chen Yan","orcid":"https://orcid.org/0000-0002-1513-1519"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Yan","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090328369","display_name":"Boyu Diao","orcid":"https://orcid.org/0000-0002-8360-7718"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Diao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104298138","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0002-7087-2416"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangda Liu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055016576","display_name":"Zhulin An","orcid":"https://orcid.org/0000-0002-7593-8293"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhulin An","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103245119","display_name":"Yongjun Xu","orcid":"https://orcid.org/0000-0001-6647-0986"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Xu","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.13724032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9666000008583069,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9666000008583069,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9589999914169312,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9532999992370605,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481469511985779},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5943790674209595},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5146106481552124},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08461493253707886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481469511985779},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5943790674209595},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5146106481552124},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08461493253707886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccgrid64434.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7400000095367432,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1508286210","https://openalex.org/W1935978687","https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2766681651","https://openalex.org/W2769686377","https://openalex.org/W2791012218","https://openalex.org/W2887822915","https://openalex.org/W2979747168","https://openalex.org/W3131215857","https://openalex.org/W3175189837","https://openalex.org/W3202552726","https://openalex.org/W4247828381","https://openalex.org/W4316660808","https://openalex.org/W4381050447","https://openalex.org/W4384705388","https://openalex.org/W4385507573","https://openalex.org/W4388736814","https://openalex.org/W4388855631","https://openalex.org/W4388979349","https://openalex.org/W4393159688","https://openalex.org/W4400644229","https://openalex.org/W4403363383","https://openalex.org/W4403794376","https://openalex.org/W6873345051","https://openalex.org/W6877416563"],"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":{"Sparse":[0,177],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4],"a":[5,9,32,56,98,152],"fundamental":[6],"operation":[7],"with":[8],"wide":[10],"range":[11],"of":[12,26,42,65,84,126,155,175],"applications":[13],"in":[14,45,116,144,147,169],"scientific":[15],"computing":[16],"and":[17,24,110,134,160],"artificial":[18],"intelligence.":[19],"However,":[20],"the":[21,40,51,62,66,71,81,117,131,139,166,173],"large":[22],"scale":[23],"sparsity":[25],"sparse":[27,47,85,170],"matrix":[28,48,86,95],"often":[29],"make":[30],"it":[31],"performance":[33,63],"bottleneck.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,89],"highlight":[39],"effectiveness":[41],"hash-based":[43],"techniques":[44],"optimizing":[46],"reordering,":[49],"introducing":[50],"Hash-based":[52],"Partition":[53],"(HBP)":[54],"format,":[55],"lightweight":[57],"SpMV":[58],"approach.":[59],"HBP":[60],"retains":[61],"benefits":[64],"2Dpartitioning":[67],"method":[68,121,142,150],"while":[69],"leveraging":[70],"hash":[72],"transformation's":[73],"ability":[74],"to":[75,130,138],"group":[76],"similar":[77],"elements,":[78],"thereby":[79],"accelerating":[80],"preprocessing":[82,118],"phase":[83],"reordering.":[87],"Additionally,":[88],"achieve":[90],"parallel":[91],"load":[92],"balancing":[93],"across":[94],"blocks":[96],"through":[97],"competitive":[99],"method.":[100],"Our":[101],"experiments,":[102],"conducted":[103],"on":[104,158,163],"both":[105],"Nvidia":[106,111],"Jetson":[107],"AGX":[108],"Orin":[109,159],"RTX":[112],"4090,":[113],"show":[114],"that":[115],"step,":[119],"our":[120,149],"offers":[122],"an":[123],"average":[124],"speedup":[125,154],"3.53":[127],"times":[128,136,157,162],"compared":[129,137],"sorting":[132],"approach":[133],"3.67":[135],"dynamic":[140],"programming":[141],"employed":[143],"Regu2D.":[145],"Furthermore,":[146],"SpMV,":[148],"achieves":[151],"maximum":[153],"3.32":[156],"3.01":[161],"RTX4090":[164],"against":[165],"CSR":[167],"format":[168],"matrices":[171],"from":[172],"University":[174],"Florida":[176],"Matrix":[178],"Collection.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}