{"id":"https://openalex.org/W4385623033","doi":"https://doi.org/10.1145/3588195.3593002","title":"Efficient Algorithm Design of Optimizing SpMV on GPU","display_name":"Efficient Algorithm Design of Optimizing SpMV on GPU","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4385623033","doi":"https://doi.org/10.1145/3588195.3593002"},"language":"en","primary_location":{"id":"doi:10.1145/3588195.3593002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3593002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","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/A5035394736","display_name":"Genshen Chu","orcid":"https://orcid.org/0000-0003-0374-1894"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Genshen Chu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061226456","display_name":"Yuanjie He","orcid":"https://orcid.org/0009-0003-7115-6846"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjie He","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770843","display_name":"Lingyu Dong","orcid":"https://orcid.org/0000-0003-0919-553X"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Dong","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044781111","display_name":"Zhezhao Ding","orcid":"https://orcid.org/0000-0003-3437-8151"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhezhao Ding","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424600","display_name":"Dandan Chen","orcid":"https://orcid.org/0000-0002-9847-5092"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dandan Chen","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081305274","display_name":"He Bai","orcid":"https://orcid.org/0000-0001-5418-0375"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuesong Wang","orcid":"https://orcid.org/0009-0000-2811-557X"},"institutions":[{"id":"https://openalex.org/I4210096139","display_name":"China Institute of Atomic Energy","ror":"https://ror.org/00v5gqm66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210096139"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["China Institute of Atomic Energy, Beijing, China"],"affiliations":[{"raw_affiliation_string":"China Institute of Atomic Energy, Beijing, China","institution_ids":["https://openalex.org/I4210096139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103142109","display_name":"Changjun Hu","orcid":"https://orcid.org/0000-0003-3857-7262"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjun Hu","raw_affiliation_strings":["University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035394736"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":2.7729,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90924381,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9904999732971191,"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/computer-science","display_name":"Computer science","score":0.8670467734336853},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7216665744781494},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5661386847496033},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.553825318813324},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5469962358474731},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5241363644599915},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.47129905223846436},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4643438458442688},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4503329396247864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08110591769218445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670467734336853},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7216665744781494},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5661386847496033},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.553825318813324},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5469962358474731},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5241363644599915},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.47129905223846436},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4643438458442688},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4503329396247864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08110591769218445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588195.3593002","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588195.3593002","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1749918898","https://openalex.org/W1990343439","https://openalex.org/W1994373416","https://openalex.org/W2009654791","https://openalex.org/W2022219663","https://openalex.org/W2035080386","https://openalex.org/W2087507944","https://openalex.org/W2088866486","https://openalex.org/W2111542840","https://openalex.org/W2128131218","https://openalex.org/W2128853364","https://openalex.org/W2162283062","https://openalex.org/W2170549342","https://openalex.org/W2263374743","https://openalex.org/W2418287910","https://openalex.org/W2503654990","https://openalex.org/W2527182050","https://openalex.org/W2544527082","https://openalex.org/W2558367073","https://openalex.org/W2570841452","https://openalex.org/W2617403939","https://openalex.org/W2751387202","https://openalex.org/W2772734385","https://openalex.org/W2808128431","https://openalex.org/W3011554625","https://openalex.org/W3093054140","https://openalex.org/W3101779959","https://openalex.org/W3106438168","https://openalex.org/W3115462165","https://openalex.org/W3131215857","https://openalex.org/W3175189837","https://openalex.org/W3199378187","https://openalex.org/W4245683599","https://openalex.org/W4247828381"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2209382646"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,110],"a":[5,82],"fundamental":[6],"building":[7],"block":[8],"for":[9,49,72,95,98],"various":[10],"numerical":[11],"computing":[12],"applications.":[13],"However,":[14],"most":[15],"existing":[16],"GPU-SpMV":[17],"approaches":[18],"may":[19],"suffer":[20],"from":[21],"either":[22],"long":[23],"preprocessing":[24],"overhead,":[25],"load":[26,73],"imbalance,":[27],"format":[28],"conversion,":[29],"bad":[30],"memory":[31,90],"access":[32,91],"patterns.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"proposed":[38,111],"two":[39],"new":[40],"SpMV":[41],"algorithms:flat":[42],"andline-enhance,":[43],"as":[44,46],"well":[45],"their":[47],"implementations,":[48],"GPU":[50],"systems":[51],"to":[52,112],"overcome":[53],"the":[54,62],"above":[55],"shortcomings.":[56],"Our":[57],"algorithms":[58,97],"work":[59],"directly":[60],"on":[61,119],"CSR":[63],"sparse":[64],"matrix":[65,120],"format.":[66],"To":[67],"achieve":[68],"high":[69],"performance:":[70],"1)":[71],"balance,":[74],"theflat":[75],"algorithm":[76,115],"uses":[77,81],"non-zero":[78,87],"splitting":[79],"andline-enhance":[80],"mix":[83],"of":[84],"row":[85],"and":[86,102,105,116],"splitting;":[88],"2)":[89],"patterns":[92],"are":[93],"designed":[94],"both":[96],"data":[99],"loading,":[100],"storing":[101],"reduction":[103],"steps;":[104],"3)":[106],"an":[107],"adaptive":[108],"approach":[109],"select":[113],"appropriate":[114],"parameters":[117],"based":[118],"characteristics.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
