{"id":"https://openalex.org/W2885034848","doi":"https://doi.org/10.1145/3225058.3225074","title":"Bandwidth Reduced Parallel SpMV on the SW26010 Many-Core Platform","display_name":"Bandwidth Reduced Parallel SpMV on the SW26010 Many-Core Platform","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2885034848","doi":"https://doi.org/10.1145/3225058.3225074","mag":"2885034848"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225074","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225074","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040022217","display_name":"Qiao Sun","orcid":"https://orcid.org/0000-0002-8770-7847"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiao Sun","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103068794","display_name":"Changyou Zhang","orcid":"https://orcid.org/0000-0003-4025-0736"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyou Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077402304","display_name":"Changmao Wu","orcid":"https://orcid.org/0000-0002-4104-1656"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changmao Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417648","display_name":"Jiajia Zhang","orcid":"https://orcid.org/0000-0003-3567-0752"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajia Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065547853","display_name":"Leisheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leisheng Li","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Haidian Qu, Beijing Shi, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040022217"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210128818"],"apc_list":null,"apc_paid":null,"fwci":1.8415,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85270867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.8821266889572144},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7727935314178467},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.658798336982727},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5959509611129761},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.49803733825683594},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4227589964866638},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41778892278671265},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.41638270020484924},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17016056180000305},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09280082583427429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8821266889572144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7727935314178467},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.658798336982727},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5959509611129761},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.49803733825683594},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4227589964866638},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41778892278671265},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.41638270020484924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17016056180000305},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09280082583427429},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225074","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3225058.3225074","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3225058.3225074","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3225058.3225074","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1232766535","display_name":null,"funder_award_id":"61379048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1428435317","display_name":null,"funder_award_id":"Grant No.:","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1432817733","display_name":null,"funder_award_id":"61672502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G198265346","display_name":null,"funder_award_id":"B14009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G466649759","display_name":null,"funder_award_id":"2017Y","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4678737013","display_name":null,"funder_award_id":"2017YFB140","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5029846496","display_name":null,"funder_award_id":"U163621","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5818079043","display_name":null,"funder_award_id":"U1636213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7429600474","display_name":null,"funder_award_id":"2017YFB1","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8340078520","display_name":null,"funder_award_id":"2017YF","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8580299944","display_name":null,"funder_award_id":"B14009","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8823009050","display_name":null,"funder_award_id":"2017YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2885034848.pdf","grobid_xml":"https://content.openalex.org/works/W2885034848.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W70618093","https://openalex.org/W92933111","https://openalex.org/W910029781","https://openalex.org/W1508286210","https://openalex.org/W1515144947","https://openalex.org/W1525132831","https://openalex.org/W1533938001","https://openalex.org/W1596846800","https://openalex.org/W1965034778","https://openalex.org/W1971520093","https://openalex.org/W1987840949","https://openalex.org/W1995649289","https://openalex.org/W2009654791","https://openalex.org/W2022219663","https://openalex.org/W2023930909","https://openalex.org/W2031460602","https://openalex.org/W2035080386","https://openalex.org/W2052993554","https://openalex.org/W2084446096","https://openalex.org/W2087507944","https://openalex.org/W2103877122","https://openalex.org/W2115052535","https://openalex.org/W2128853364","https://openalex.org/W2162283062","https://openalex.org/W2184741585","https://openalex.org/W2284629249","https://openalex.org/W2410461480","https://openalex.org/W2475126267","https://openalex.org/W2505742200","https://openalex.org/W2535926538","https://openalex.org/W2561247022","https://openalex.org/W2576489192","https://openalex.org/W2749559108","https://openalex.org/W3125710003","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2031026393","https://openalex.org/W2063611263","https://openalex.org/W2030992542","https://openalex.org/W1541167181","https://openalex.org/W4389888442","https://openalex.org/W2149529325","https://openalex.org/W3103168911","https://openalex.org/W2157146993","https://openalex.org/W4308090217","https://openalex.org/W2120768584"],"abstract_inverted_index":{"SpMV":[0,58,98],"(Sparse":[1],"Matrix-Vector":[2],"multiplication),":[3],"in":[4,26,55,59,116,199,257,267],"its":[5,68],"simplest":[6],"form":[7],"y":[8],"=":[9],"Ax,":[10],"multiplies":[11],"a":[12,16,21,39,130,191,258,262,268],"sparse":[13,197],"matrix":[14],"with":[15],"dense":[17],"vector":[18],"and":[19,77,183],"is":[20,70,106,134,178,188,215,254,265],"widely":[22],"used":[23,196],"computing":[24,234],"primitive":[25],"the":[27,32,56,60,91,100,117,123,143,152,155,159,163,170,200,212,218,221,228,233,250,272],"domain":[28],"of":[29,48,94,112,154,193,202,241,249],"HPC.":[30],"On":[31],"newly":[33],"SW26010":[34],"many-core":[35,144],"platform,":[36],"we":[37,141],"propose":[38],"highly":[40],"efficient":[41],"CSR":[42,61],"(Compressed":[43],"Storage":[44],"Row)":[45],"based":[46,260],"implementation":[47],"parallel":[49],"SpMV,":[50],"referred":[51],"to":[52,79,136,150,172],"as":[53],"SWCSR-SpMV":[54,236,253],"sequel.":[57],"format":[62],"can":[63,114,126,237],"be":[64,127],"trivially":[65],"parallelized":[66],"but":[67],"performance":[69,97,213],"majorly":[71],"impeded":[72],"by":[73,180,217],"memory":[74,82,139],"access":[75,83,224],"efficiency,":[76],"therefore":[78],"leverage":[80,173],"high-throughput":[81],"mechanism":[84],"while":[85],"avoiding":[86],"redundant":[87,138],"bandwidth":[88],"usage":[89],"becomes":[90],"major":[92],"goal":[93],"designing":[95],"high":[96,164],"on":[99,190,271],"target":[101],"platform.":[102],"The":[103],"original":[104],"problem":[105],"sequentially":[107],"partitioned":[108],"into":[109,146],"row-slices,":[110],"each":[111],"which":[113],"reside":[115],"fast":[118],"scratchpad":[119],"memory,":[120],"so":[121],"that":[122],"loaded":[124],"x'es":[125],"reused;":[128],"meanwhile,":[129],"dynamic":[131,184],"look-ahead":[132],"scheme":[133],"applied":[135,256],"avoid":[137],"access;":[140],"split":[142],"mesh":[145],"smaller":[147],"communication":[148],"scope":[149],"facilitate":[151],"sharing":[153],"common":[156],"data":[157,167,205,223],"across":[158],"working":[160],"threads":[161],"via":[162],"speed":[165],"on-mesh":[166],"bus.":[168],"Beyond":[169],"above,":[171],"massive":[174],"parallelism":[175],"balanced":[176],"workload":[177],"ensured":[179],"both":[181],"static":[182],"means.":[185],"Performance":[186],"evaluation":[187],"done":[189],"benchmark":[192],"36":[194],"frequently":[195],"matrices":[198],"fields":[201],"graph":[203],"computing,":[204],"mining,":[206],"computational":[207],"fluid":[208],"dynamics,":[209],"etc..":[210],"While":[211],"upper-bound":[214],"defined":[216],"ratio":[219],"between":[220],"minimal":[222],"volume":[225],"required":[226],"against":[227],"practically":[229],"optimal":[230],"bandwidth,":[231],"ignoring":[232],"overhead,":[235],"achieve":[238],"an":[239],"efficiency":[240],"nearly":[242],"87%,":[243],"maintaining":[244],"over":[245],"75%":[246],"for":[247],"1/3":[248],"testing":[251],"matrices.":[252],"further":[255],"PETSc":[259],"application,":[261],"1.75x-2.6x":[263],"speedup":[264],"sustained":[266],"multi-process":[269],"environment":[270],"Sunway":[273],"TaiHuLight":[274],"supercomputer.":[275]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
