{"id":"https://openalex.org/W4223467872","doi":"https://doi.org/10.1145/3512770","title":"fgSpMSpV: A Fine-grained Parallel SpMSpV Framework on HPC Platforms","display_name":"fgSpMSpV: A Fine-grained Parallel SpMSpV Framework on HPC Platforms","publication_year":2022,"publication_date":"2022-04-11","ids":{"openalex":"https://openalex.org/W4223467872","doi":"https://doi.org/10.1145/3512770"},"language":"en","primary_location":{"id":"doi:10.1145/3512770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512770","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-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/A5035942362","display_name":"Yuedan Chen","orcid":"https://orcid.org/0000-0001-5665-268X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuedan Chen","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5665-268X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107094004","display_name":"Guoqing Xiao","orcid":"https://orcid.org/0000-0001-5008-4829"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Xiao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-5008-4829","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0002-2635-7716","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, and National Supercomputing Center in Changsha, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016445191","display_name":"Francesco Piccialli","orcid":"https://orcid.org/0000-0002-5179-2496"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Piccialli","raw_affiliation_strings":["Department of Electrical Engineering and Information Technologies,University of Naples Federico II, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5179-2496","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technologies,University of Naples Federico II, Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015993565","display_name":"Albert Y. Zomaya","orcid":"https://orcid.org/0000-0002-3090-1059"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Albert Y. Zomaya","raw_affiliation_strings":["School of Information Technologies, University of Sydney, Sidney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3090-1059","affiliations":[{"raw_affiliation_string":"School of Information Technologies, University of Sydney, Sidney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5035942362"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":3.0309,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91408072,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9976999759674072,"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":0.9944999814033508,"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":0.8219716548919678},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.8065176010131836},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.79427170753479},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5828099250793457},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5233047008514404},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5038685202598572},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.48554345965385437},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.48161548376083374},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47917118668556213},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.45483630895614624},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38625916838645935},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.10920125246047974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219716548919678},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8065176010131836},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.79427170753479},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5828099250793457},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5233047008514404},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5038685202598572},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.48554345965385437},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.48161548376083374},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47917118668556213},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.45483630895614624},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38625916838645935},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.10920125246047974},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3512770","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3512770","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5188181803","display_name":null,"funder_award_id":"62172157, 61860206011 and 61806077","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":43,"referenced_works":["https://openalex.org/W1783256592","https://openalex.org/W1893178273","https://openalex.org/W1961697688","https://openalex.org/W1980282429","https://openalex.org/W1999085008","https://openalex.org/W2022219663","https://openalex.org/W2035080386","https://openalex.org/W2089437293","https://openalex.org/W2091786461","https://openalex.org/W2154111453","https://openalex.org/W2170721150","https://openalex.org/W2278138779","https://openalex.org/W2290443447","https://openalex.org/W2294347342","https://openalex.org/W2298920323","https://openalex.org/W2413890865","https://openalex.org/W2479693678","https://openalex.org/W2501699529","https://openalex.org/W2535926538","https://openalex.org/W2542072367","https://openalex.org/W2582955817","https://openalex.org/W2588054100","https://openalex.org/W2626052469","https://openalex.org/W2781614977","https://openalex.org/W2891325938","https://openalex.org/W2891818448","https://openalex.org/W2904719450","https://openalex.org/W2919538836","https://openalex.org/W2922815438","https://openalex.org/W2923126305","https://openalex.org/W2945434221","https://openalex.org/W2964210765","https://openalex.org/W2965706220","https://openalex.org/W2971745895","https://openalex.org/W2977678017","https://openalex.org/W2981086990","https://openalex.org/W2996522450","https://openalex.org/W3014934202","https://openalex.org/W3020586295","https://openalex.org/W3038822515","https://openalex.org/W3047208409","https://openalex.org/W3110597019","https://openalex.org/W4230422651"],"related_works":["https://openalex.org/W2582456645","https://openalex.org/W1509211761","https://openalex.org/W3176814699","https://openalex.org/W2098513105","https://openalex.org/W1980282429","https://openalex.org/W4200522199","https://openalex.org/W2998104365","https://openalex.org/W3089579782","https://openalex.org/W2126944241","https://openalex.org/W4223467872"],"abstract_inverted_index":{"Sparse":[0,167],"matrix-sparse":[1],"vector":[2],"(SpMSpV)":[3],"multiplication":[4],"is":[5,208],"one":[6],"of":[7,44,50,63,110,140,157,203,231,251],"the":[8,48,56,61,83,105,131,135,141,160,182,187,196,204,219,229,238,243,249,258],"fundamental":[9],"and":[10,17,23,52,107,114,118,137,148,165,216,242],"important":[11],"operations":[12],"in":[13,152],"many":[14],"high-performance":[15,36],"scientific":[16],"engineering":[18],"applications.":[19,88],"The":[20],"inherent":[21],"irregularity":[22],"poor":[24],"data":[25,46],"locality":[26],"lead":[27],"to":[28,32,81,103,129,134,179,218,233,253],"two":[29],"main":[30,119],"challenges":[31,84],"scaling":[33],"SpMSpV":[34,72,120,240],"over":[35,237,257],"computing":[37,64,183],"(HPC)":[38],"systems:":[39],"(i)":[40],"a":[41,69,155,191,225],"large":[42],"amount":[43],"redundant":[45,147],"limits":[47,60],"utilization":[49],"bandwidth":[51],"parallel":[53,71,127],"resources;":[54],"(ii)":[55],"irregular":[57],"access":[58],"pattern":[59],"exploitation":[62],"resources.":[65,184],"This":[66],"paper":[67],"proposes":[68],"fine-grained":[70,161],"(":[73],"fgSpMSpV":[74,90,123,174,185,207,223,247],")":[75],"framework":[76],"on":[77,186,210,224],"Sunway":[78,142,188],"TaihuLight":[79,189],"supercomputer":[80],"alleviate":[82],"for":[85],"large-scale":[86],"real-world":[87],"First,":[89],"adopts":[91],"an":[92,125,211],"MPI":[93],"\\(":[94,98,234,254],"+":[95],"\\)":[96,100,236,256],"OpenMP":[97],"+X":[99],"parallelization":[101],"model":[102],"exploit":[104],"multi-stage":[106],"hybrid":[108],"parallelism":[109,136],"heterogeneous":[111],"HPC":[112],"architectures":[113],"accelerate":[115],"both":[116],"pre-/post-processing":[117],"computation.":[121],"Second,":[122],"utilizes":[124],"adaptive":[126],"execution":[128],"reduce":[130],"pre-processing,":[132],"adapt":[133],"memory":[138,150],"hierarchy":[139],"system,":[143],"while":[144],"still":[145],"tame":[146],"random":[149],"accesses":[151],"SpMSpV,":[153],"including":[154],"set":[156],"techniques":[158,178,199],"like":[159],"partitioner,":[162],"re-collection":[163],"method,":[164],"Compressed":[166],"Column":[168],"Vector":[169],"(CSCV)":[170],"matrix":[171],"format.":[172],"Third,":[173],"uses":[175],"several":[176],"optimization":[177,198],"further":[180],"utilize":[181],"gains":[190],"noticeable":[192],"performance":[193],"improvement":[194],"from":[195],"key":[197],"with":[200],"various":[201],"sparsity":[202],"input.":[205],"Additionally,":[206],"implemented":[209],"NVIDIA":[212],"Tesal":[213],"P100":[214,226],"GPU":[215,227],"applied":[217],"breath-first-search":[220],"(BFS)":[221],"application.":[222],"obtains":[228],"speedup":[230,250],"up":[232,252],"134.38\\times":[235],"state-of-the-art":[239],"algorithms,":[241],"BFS":[244],"application":[245],"using":[246],"achieves":[248],"21.68\\times":[255],"state-of-the-arts.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
