{"id":"https://openalex.org/W4388738169","doi":"https://doi.org/10.1145/3606043.3606057","title":"GTLB:A Load-Balanced SpMV Computation Method on GPU","display_name":"GTLB:A Load-Balanced SpMV Computation Method on GPU","publication_year":2023,"publication_date":"2023-06-17","ids":{"openalex":"https://openalex.org/W4388738169","doi":"https://doi.org/10.1145/3606043.3606057"},"language":"en","primary_location":{"id":"doi:10.1145/3606043.3606057","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606043.3606057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on High Performance Compilation, Computing and Communications","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/A5011285232","display_name":"J. D. Jiang","orcid":"https://orcid.org/0009-0003-6689-959X"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiafan Jiang","raw_affiliation_strings":["Department of Computer Applications and Technology, Qinghai University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Applications and Technology, Qinghai University, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945411","display_name":"Jianqiang Huang","orcid":"https://orcid.org/0000-0002-4454-7919"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Huang","raw_affiliation_strings":["Department of Computer Applications and Technology, Qinghai University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Applications and Technology, Qinghai University, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003261630","display_name":"Haodong Bian","orcid":"https://orcid.org/0000-0003-0907-288X"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Bian","raw_affiliation_strings":["Department of Computer Applications and Technology, Qinghai University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Applications and Technology, Qinghai University, China","institution_ids":["https://openalex.org/I116265982"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011285232"],"corresponding_institution_ids":["https://openalex.org/I116265982"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18806787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.989300012588501,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.989300012588501,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9483000040054321,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9444000124931335,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483025193214417},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6007548570632935},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5959039330482483},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4852285385131836},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3217977285385132},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10669592022895813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483025193214417},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6007548570632935},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5959039330482483},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4852285385131836},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3217977285385132},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10669592022895813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3606043.3606057","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3606043.3606057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on High Performance Compilation, Computing and Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G6044928846","display_name":null,"funder_award_id":"No.62062059,No.62162053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2009654791","https://openalex.org/W2088866486","https://openalex.org/W2104509996","https://openalex.org/W2126004407","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2142356482","https://openalex.org/W2157146993","https://openalex.org/W2559809597","https://openalex.org/W2571103886","https://openalex.org/W2791012218","https://openalex.org/W2976670629","https://openalex.org/W3010221833","https://openalex.org/W3094263445","https://openalex.org/W3096209535","https://openalex.org/W3156646978","https://openalex.org/W3175189837","https://openalex.org/W3176901945","https://openalex.org/W3194527970","https://openalex.org/W4247712932"],"related_works":["https://openalex.org/W3213381848","https://openalex.org/W2005148983","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2602637431","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2939411666","https://openalex.org/W1973046741","https://openalex.org/W3189307731"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Vector":[1],"Multiplication":[2],"(SpMV)":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"in":[8],"the":[9,30,54,90,119],"field":[10],"of":[11,15,32,40,51,76,121],"scientific":[12],"computing.":[13],"Optimization":[14,50],"SpMV\u2019s":[16],"computational":[17,48],"performance":[18,43,60,68],"can":[19,37,57],"bring":[20,58],"significant":[21],"benefits":[22],"to":[23,93],"its":[24],"usage.":[25],"In":[26],"recent":[27],"years,":[28],"with":[29,74],"development":[31],"GPU":[33,55,72],"hardware":[34],"technology,":[35],"SpMV":[36,52,122],"provide":[38],"tens":[39],"times":[41],"better":[42],"than":[44],"CPUs":[45],"for":[46,66,109],"simple":[47],"tasks.":[49],"on":[53,89],"platform":[56],"great":[59],"improvements.":[61],"Load":[62],"balancing":[63],"is":[64],"crucial":[65],"achieving":[67],"improvements":[69],"when":[70],"using":[71],"platforms":[73],"thousands":[75],"computing":[77],"cores.":[78],"This":[79],"study":[80,102],"proposes":[81],"a":[82,105],"two-level":[83],"average":[84],"block":[85],"partitioning":[86],"strategy":[87],"based":[88],"CSR":[91],"format":[92],"achieve":[94],"balanced":[95],"block-level":[96],"and":[97,115],"thread-level":[98],"task":[99],"partitioning.":[100],"The":[101],"also":[103],"designed":[104],"parallel":[106],"merge":[107],"scheme":[108],"data":[110],"merging":[111],"among":[112],"threads,":[113],"warps,":[114],"blocks,":[116],"further":[117],"improving":[118],"parallelism":[120],"computation.":[123]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}