{"id":"https://openalex.org/W2985041356","doi":"https://doi.org/10.1177/1094342019886628","title":"Sparse matrix partitioning for optimizing SpMV on CPU-GPU heterogeneous platforms","display_name":"Sparse matrix partitioning for optimizing SpMV on CPU-GPU heterogeneous platforms","publication_year":2019,"publication_date":"2019-11-14","ids":{"openalex":"https://openalex.org/W2985041356","doi":"https://doi.org/10.1177/1094342019886628","mag":"2985041356"},"language":"en","primary_location":{"id":"doi:10.1177/1094342019886628","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342019886628","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342019886628","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342019886628","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083016757","display_name":"Mohamed Akrem Benatia","orcid":"https://orcid.org/0000-0003-1779-2705"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Akrem Benatia","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1779-2705","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046211358","display_name":"Weixing Ji","orcid":"https://orcid.org/0000-0002-3250-0435"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weixing Ji","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3250-0435","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672331","display_name":"Yizhuo Wang","orcid":"https://orcid.org/0000-0002-1288-331X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhuo Wang","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101794838","display_name":"Feng Shi","orcid":"https://orcid.org/0000-0001-5175-9760"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Shi","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046211358"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":1.5556,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.83562328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"34","issue":"1","first_page":"66","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9972000122070312,"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":0.8226248025894165},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7673854231834412},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7324370741844177},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7108067274093628},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6737964749336243},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5263791680335999},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5163939595222473},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.5080047249794006},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.49665647745132446},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4694273769855499},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.45456862449645996},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.44236406683921814},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4227278232574463},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3303728997707367},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17271828651428223},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09631726145744324},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.07496803998947144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07103011012077332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226248025894165},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7673854231834412},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7324370741844177},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7108067274093628},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6737964749336243},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5263791680335999},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5163939595222473},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5080047249794006},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.49665647745132446},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4694273769855499},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.45456862449645996},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.44236406683921814},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4227278232574463},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3303728997707367},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17271828651428223},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09631726145744324},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.07496803998947144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07103011012077332},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342019886628","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342019886628","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342019886628","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1177/1094342019886628","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342019886628","pdf_url":"https://journals.sagepub.com/doi/pdf/10.1177/1094342019886628","source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8894184016","display_name":null,"funder_award_id":"2017YFB0202500","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":32,"referenced_works":["https://openalex.org/W610778723","https://openalex.org/W1588915715","https://openalex.org/W1600301286","https://openalex.org/W1964357740","https://openalex.org/W1971367716","https://openalex.org/W1981557297","https://openalex.org/W1992476323","https://openalex.org/W2011159963","https://openalex.org/W2022219663","https://openalex.org/W2023930909","https://openalex.org/W2025397485","https://openalex.org/W2025890876","https://openalex.org/W2031460602","https://openalex.org/W2035080386","https://openalex.org/W2040556424","https://openalex.org/W2050127041","https://openalex.org/W2091883426","https://openalex.org/W2097025565","https://openalex.org/W2103877122","https://openalex.org/W2105545110","https://openalex.org/W2128539477","https://openalex.org/W2130289795","https://openalex.org/W2137226992","https://openalex.org/W2137983211","https://openalex.org/W2153635508","https://openalex.org/W2162283062","https://openalex.org/W2167334577","https://openalex.org/W2342906597","https://openalex.org/W2568669383","https://openalex.org/W2570841452","https://openalex.org/W2579077247","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W1972148443","https://openalex.org/W2061938028","https://openalex.org/W2293771254","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2914631005","https://openalex.org/W2123154672","https://openalex.org/W2032786851","https://openalex.org/W2952630098"],"abstract_inverted_index":{"Sparse":[0],"matrix\u2013vector":[1],"multiplication":[2],"(SpMV)":[3],"kernel":[4,21,147],"dominates":[5],"the":[6,14,43,46,61,81,92,95,99,103,114,145,170,195,198,204],"computing":[7,144],"cost":[8],"in":[9,135,203],"numerous":[10],"applications.":[11],"Most":[12],"of":[13,28,45,57,83,94,161],"existing":[15],"studies":[16],"dedicated":[17],"to":[18,66,112,124,154,193,197],"improving":[19],"this":[20,131,136],"have":[22,40],"been":[23],"targeting":[24],"just":[25],"one":[26],"type":[27],"processing":[29,36,72],"units,":[30],"mainly":[31],"multicore":[32],"CPUs":[33],"or":[34],"graphics":[35],"units":[37],"(GPUs),":[38],"and":[39,98,158,176,200],"not":[41,107],"explored":[42],"potential":[44],"recent,":[47],"rapidly":[48],"emerging,":[49],"CPU-GPU":[50,140,162],"heterogeneous":[51,59,141,163],"platforms.":[52,164],"To":[53,129],"take":[54],"full":[55],"advantage":[56],"these":[58],"systems,":[60],"input":[62,96,115,171],"sparse":[63,85,116,122,152,180,213],"matrix":[64,97,117,172],"has":[65],"be":[67],"partitioned":[68],"on":[69,91,110,120,215],"different":[70,151,217],"available":[71,202],"units.":[73],"The":[74,165],"partitioning":[75],"problem":[76],"is":[77,190],"more":[78],"challenging":[79],"with":[80],"existence":[82],"many":[84],"formats":[86,153,181],"whose":[87],"performances":[88],"depend":[89,109],"both":[90],"sparsity":[93],"used":[100,192],"hardware.":[101],"Thus,":[102],"best":[104,179],"performance":[105,157,185,222],"does":[106],"only":[108],"how":[111],"partition":[113],"but":[118],"also":[119],"which":[121],"format":[123],"use":[125],"for":[126,143],"each":[127],"partition.":[128],"address":[130],"challenge,":[132],"we":[133],"propose":[134],"article":[137],"a":[138,220],"new":[139],"method":[142],"SpMV":[146],"that":[148],"combines":[149],"between":[150],"achieve":[155],"better":[156,159],"utilization":[160],"proposed":[166],"solution":[167],"horizontally":[168],"partitions":[169],"into":[173],"multiple":[174],"block-rows":[175,196],"predicts":[177],"their":[178],"using":[182,209],"machine":[183],"learning-based":[184],"models.":[186],"A":[187],"mapping":[188],"algorithm":[189],"then":[191],"assign":[194],"CPU":[199],"GPU(s)":[201],"system.":[205],"Our":[206],"experimental":[207],"results":[208],"real-world":[210],"large":[211],"unstructured":[212],"matrices":[214],"two":[216],"machines":[218],"show":[219],"noticeable":[221],"improvement.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}