{"id":"https://openalex.org/W2208875625","doi":"https://doi.org/10.1137/14097135x","title":"A Task-Scheduling Approach for Efficient Sparse Symmetric Matrix-Vector Multiplication on a GPU","display_name":"A Task-Scheduling Approach for Efficient Sparse Symmetric Matrix-Vector Multiplication on a GPU","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2208875625","doi":"https://doi.org/10.1137/14097135x","mag":"2208875625"},"language":"en","primary_location":{"id":"doi:10.1137/14097135x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/14097135x","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific 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/A5024137584","display_name":"Piotr Mironowicz","orcid":"https://orcid.org/0000-0003-4122-5372"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"P. Mironowicz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043653093","display_name":"Adam Dziekonski","orcid":"https://orcid.org/0000-0003-1045-3268"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Dziekonski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073551397","display_name":"Micha\u0142 Mrozowski","orcid":"https://orcid.org/0000-0002-1110-8717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. Mrozowski","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024137584"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.323,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.61142651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"37","issue":"6","first_page":"C643","last_page":"C666"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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":0.9979000091552734,"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/speedup","display_name":"Speedup","score":0.7460244297981262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7281108498573303},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6798310279846191},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6587258577346802},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5698505640029907},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4947780966758728},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.47335219383239746},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.4525938034057617},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.442403107881546},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.42597830295562744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42204374074935913},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38243919610977173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18764543533325195},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.18177595734596252}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7460244297981262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281108498573303},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6798310279846191},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6587258577346802},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5698505640029907},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4947780966758728},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.47335219383239746},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.4525938034057617},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.442403107881546},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.42597830295562744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42204374074935913},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38243919610977173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18764543533325195},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.18177595734596252},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/14097135x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/14097135x","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W104109059","https://openalex.org/W1506342804","https://openalex.org/W1587796446","https://openalex.org/W1596846800","https://openalex.org/W1653630692","https://openalex.org/W1967066104","https://openalex.org/W1987393840","https://openalex.org/W1987840949","https://openalex.org/W1990832096","https://openalex.org/W1994373416","https://openalex.org/W2018419001","https://openalex.org/W2023871968","https://openalex.org/W2024029196","https://openalex.org/W2049500052","https://openalex.org/W2084446096","https://openalex.org/W2094333709","https://openalex.org/W2095420020","https://openalex.org/W2097479462","https://openalex.org/W2101511474","https://openalex.org/W2102538901","https://openalex.org/W2103877122","https://openalex.org/W2109493417","https://openalex.org/W2114977680","https://openalex.org/W2124007994","https://openalex.org/W2130748128","https://openalex.org/W2152549562","https://openalex.org/W2167868137","https://openalex.org/W3101779959"],"related_works":["https://openalex.org/W2526784484","https://openalex.org/W2077700531","https://openalex.org/W1509943448","https://openalex.org/W2074431240","https://openalex.org/W2048297217","https://openalex.org/W2348330046","https://openalex.org/W2100843445","https://openalex.org/W2061572227","https://openalex.org/W3149476094","https://openalex.org/W1987177655"],"abstract_inverted_index":{"In":[0],"this":[1,67],"paper,":[2],"a":[3,101,118,154,190],"task-scheduling":[4,96],"approach":[5,144,185],"to":[6,15,41,61,72,110,121,153,162,172,188],"efficiently":[7],"calculating":[8],"sparse":[9,31,89,146,179],"symmetric":[10,32,147,180],"matrix-vector":[11,148],"products":[12,149],"and":[13,48,107,120,174],"designed":[14],"run":[16],"on":[17,117,127],"graphics":[18,105],"processing":[19,129],"units":[20,130],"(GPUs)":[21],"is":[22,27,39,55,98,108],"presented.":[23],"The":[24,63,91,137],"main":[25],"premise":[26],"that,":[28],"for":[29,145,178],"many":[30],"matrices":[33],"occurring":[34],"in":[35,45,50,57,66,133,151,157],"common":[36],"applications,":[37],"it":[38],"possible":[40],"obtain":[42],"significant":[43,191],"reductions":[44],"memory":[46,158],"usage":[47],"improvements":[49],"performance":[51,92,112],"when":[52],"the":[53,74,79,86,94,111,124,134,142,182],"matrix":[54,164],"prepared":[56],"certain":[58],"ways":[59],"prior":[60],"computation.":[62],"preprocessing":[64],"proposed":[65,95,143,183],"paper":[68],"employs":[69],"task":[70],"scheduling":[71],"overcome":[73],"difficulties":[75],"that":[76,141],"have":[77],"suppressed":[78],"development":[80],"of":[81,85,88,93,113,197],"methods":[82],"taking":[83],"advantage":[84],"symmetry":[87],"matrices.":[90],"method":[97],"verified":[99],"using":[100],"Kepler":[102],"(Tesla":[103],"K40c)":[104],"accelerator,":[106],"compared":[109,161],"cuSPARSE":[114,173],"library":[115],"functions":[116,122,177],"GPU":[119],"from":[123],"Intel":[125,175],"MKL":[126,176],"central":[128],"(CPUs)":[131],"executed":[132],"parallel":[135],"mode.":[136],"obtained":[138],"results":[139,150],"indicate":[140],"up":[152],"40%":[155],"reduction":[156],"usage,":[159],"as":[160],"nonsymmetric":[163],"storage":[165],"formats,":[166],"while":[167],"retaining":[168],"good":[169],"throughput.":[170],"Compared":[171],"matrices,":[181],"TSMV":[184],"allowed":[186],"us":[187],"achieve":[189],"speedup":[192],"(of":[193],"over":[194],"one":[195],"order":[196],"magnitude).":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}