{"id":"https://openalex.org/W1994373416","doi":"https://doi.org/10.1137/120900216","title":"Compressed Multirow Storage Format for Sparse Matrices on Graphics Processing Units","display_name":"Compressed Multirow Storage Format for Sparse Matrices on Graphics Processing Units","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1994373416","doi":"https://doi.org/10.1137/120900216","mag":"1994373416"},"language":"en","primary_location":{"id":"doi:10.1137/120900216","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120900216","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1203.2946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zbigniew Koza","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zbigniew Koza","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Maciej Matyka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maciej Matyka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sebastian Szkoda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Szkoda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"\u0141ukasz Miros\u0142aw","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0141ukasz Miros\u0142aw","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4106,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94331259,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"2","first_page":"C219","last_page":"C239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8587999939918518,"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":0.8587999939918518,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.04089999943971634,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.010599999688565731,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/sparse-matrix","display_name":"Sparse matrix","score":0.7063999772071838},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6904000043869019},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6726999878883362},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.46549999713897705},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.4530999958515167},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42100000381469727},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4203000068664551},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.41029998660087585}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7063999772071838},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911999940872192},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4945000112056732},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C124851039","wikidata":"https://www.wikidata.org/wiki/Q2665459","display_name":"Compressed sensing","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3246999979019165},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C18945957","wikidata":"https://www.wikidata.org/wiki/Q5597193","display_name":"Graphics hardware","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/120900216","is_oa":false,"landing_page_url":"https://doi.org/10.1137/120900216","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"},{"id":"pmh:oai:arXiv.org:1203.2946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1203.2946","pdf_url":"https://arxiv.org/pdf/1203.2946","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.756.2850","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.756.2850","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1203.2946.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1203.2946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1203.2946","pdf_url":"https://arxiv.org/pdf/1203.2946","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5374134968","display_name":null,"funder_award_id":"European Social Fund","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1989568755","https://openalex.org/W2021265080","https://openalex.org/W2084446096","https://openalex.org/W2095836023","https://openalex.org/W2097479462","https://openalex.org/W2099625934","https://openalex.org/W4243261006"],"related_works":[],"abstract_inverted_index":{"A":[0],"new":[1,49],"format":[2,23,31,50],"for":[3,9,47,53],"storing":[4],"sparse":[5,11,56],"matrices":[6,57],"is":[7,51],"proposed":[8],"efficient":[10],"matrix-vector":[12],"(SpMV)":[13],"product":[14],"calculation":[15],"on":[16,58],"modern":[17],"graphics":[18],"processing":[19],"units":[20],"(GPUs).":[21],"This":[22],"extends":[24],"the":[25,48,84,92,95],"standard":[26],"compressed":[27],"row":[28],"storage":[29],"(CRS)":[30],"and":[32,38,60,63,72,79],"can":[33],"be":[34],"quickly":[35],"converted":[36],"to":[37,88],"from":[39],"it.":[40],"Computational":[41],"performance":[42],"of":[43,67,86,94],"two":[44],"SpMV":[45],"kernels":[46],"determined":[52],"over":[54,91],"130":[55],"Fermi-class":[59],"Kepler-class":[61],"GPUs":[62],"compared":[64],"with":[65],"that":[66],"five":[68,96],"existing":[69],"generic":[70],"algorithms":[71],"industrial":[73],"implementations,":[74],"including":[75],"Nvidia":[76],"cuSparse":[77],"CSR":[78],"HYB":[80],"kernels.":[81,98],"We":[82],"found":[83],"speedup":[85],"up":[87],"$\\approx":[89],"60%$":[90],"best":[93],"alternative":[97]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}