{"id":"https://openalex.org/W3099744258","doi":"https://doi.org/10.1109/ipdpsw.2012.211","title":"Sparse Matrix-vector Multiplication on GPGPU Clusters: A New Storage Format and a Scalable Implementation","display_name":"Sparse Matrix-vector Multiplication on GPGPU Clusters: A New Storage Format and a Scalable Implementation","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W3099744258","doi":"https://doi.org/10.1109/ipdpsw.2012.211","mag":"3099744258"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2012.211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/1112.5588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038048025","display_name":"Moritz Kreutzer","orcid":"https://orcid.org/0000-0002-7822-9468"},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Moritz Kreutzer","raw_affiliation_strings":["Erlangen Regional Computing Center, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen Regional Computing Center, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Erlangen Regional Computing Center, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056729987","display_name":"Holger Fehske","orcid":"https://orcid.org/0000-0003-2146-8203"},"institutions":[{"id":"https://openalex.org/I36522303","display_name":"Universit\u00e4t Greifswald","ror":"https://ror.org/00r1edq15","country_code":"DE","type":"education","lineage":["https://openalex.org/I36522303"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Holger Fehske","raw_affiliation_strings":["Ernst Moritz Arndt University\uc2a0of Greifswald, Greifswald, Germany"],"affiliations":[{"raw_affiliation_string":"Ernst Moritz Arndt University\uc2a0of Greifswald, Greifswald, Germany","institution_ids":["https://openalex.org/I36522303"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070137241","display_name":"Achim Basermann","orcid":"https://orcid.org/0000-0003-3637-3231"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Achim Basermann","raw_affiliation_strings":["Simulation and Software Technology, German AeroSpace Center (DLR), Cologne, Germany"],"affiliations":[{"raw_affiliation_string":"Simulation and Software Technology, German AeroSpace Center (DLR), Cologne, Germany","institution_ids":["https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113506287","display_name":"A. R. Bishop","orcid":null},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan R. Bishop","raw_affiliation_strings":["Theory, Simulation and Computation Directorate, Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Theory, Simulation and Computation Directorate, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":43,"citation_normalized_percentile":{"value":0.992345,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Distributed Storage Systems and Network Coding","score":0.9995,"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":"Distributed Storage Systems and Network Coding","score":0.9995,"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 Performance Optimization","score":0.9995,"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/T11612","display_name":"Optimization Methods in Machine Learning","score":0.9984,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/gpu-computing","display_name":"GPU Computing","score":0.514583},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.44487754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482922},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8280867},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7470022},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6856858},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6674238},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.63654244},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5829358},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.57890576},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.57151324},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5473778},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.44487754},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4162844},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.35932684},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12433225},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.07445127},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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}],"mesh":[],"locations_count":5,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2012.211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1112.5588","pdf_url":"http://arxiv.org/pdf/1112.5588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://elib.dlr.de/75140/1/ipdps12_29_02_12.pdf","pdf_url":"https://elib.dlr.de/75140/1/ipdps12_29_02_12.pdf","source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":["Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1112.5588","pdf_url":"https://arxiv.org/pdf/1112.5588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.1112.5588","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1112.5588","pdf_url":"http://arxiv.org/pdf/1112.5588","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W2164904521","https://openalex.org/W3099744258"],"referenced_works_count":13,"referenced_works":["https://openalex.org/W1556024611","https://openalex.org/W1568530854","https://openalex.org/W1588915715","https://openalex.org/W1941137163","https://openalex.org/W1961194538","https://openalex.org/W1992303919","https://openalex.org/W1995649289","https://openalex.org/W2076361081","https://openalex.org/W2097479462","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2518567779","https://openalex.org/W2951272196"],"related_works":["https://openalex.org/W3048701459","https://openalex.org/W2792081825","https://openalex.org/W240129890","https://openalex.org/W2389600408","https://openalex.org/W2370314112","https://openalex.org/W2364044215","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W1963859303","https://openalex.org/W1912958759"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(spMVM)":[3],"is":[4,39],"the":[5,25,45,50,59,66,70,76,88,101],"dominant":[6],"operation":[7],"in":[8],"many":[9],"sparse":[10],"solvers.":[11],"We":[12],"investigate":[13],"performance":[14,94,98],"properties":[15],"of":[16,20,29,87,108,137],"spMVM":[17,72,126],"with":[18],"matrices":[19],"various":[21],"sparsity":[22,117],"patterns":[23,118],"on":[24,75,100,123],"nVidia":[26],"\"Fermi\"":[27],"class":[28],"GPGPUs.":[30],"A":[31],"new":[32],"\"padded":[33],"jagged":[34],"diagonals":[35],"storage\"":[36],"(pJDS)":[37],"format":[38,68],"proposed":[40],"which":[41],"may":[42],"substantially":[43],"reduce":[44],"memory":[46,73],"overhead":[47],"intrinsic":[48],"to":[49,80,85,127],"widespread":[51],"ELLPACK-R":[52,89],"scheme":[53],"while":[54],"making":[55],"no":[56],"assumptions":[57],"about":[58],"matrix":[60,109],"structure.":[61],"In":[62],"our":[63],"test":[64],"scenarios":[65],"pJDS":[67],"cuts":[69],"overall":[71],"footprint":[74],"GPGPU":[77],"by":[78],"up":[79],"70%,":[81],"and":[82,139],"achieves":[83],"91%":[84],"130%":[86],"performance.":[90],"Using":[91],"a":[92,129],"suitable":[93],"model":[95],"we":[96,119],"identify":[97],"bottlenecks":[99],"node":[102],"level":[103],"that":[104],"invalidate":[105],"some":[106],"types":[107],"structures":[110],"for":[111],"efficient":[112,135],"multi-GPGPU":[113],"parallelization.":[114],"For":[115],"appropriate":[116],"extend":[120],"previous":[121],"work":[122],"distributed-memory":[124],"parallel":[125],"demonstrate":[128],"scalable":[130],"hybrid":[131],"MPI-GPGPU":[132],"code,":[133],"achieving":[134],"overlap":[136],"communication":[138],"computation.":[140]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3099744258","counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2024-11-06T04:42:08.005470","created_date":"2020-11-23"}
