{"id":"https://openalex.org/W2011159963","doi":"https://doi.org/10.1145/2016741.2016744","title":"A model-driven partitioning and auto-tuning integrated framework for sparse matrix-vector multiplication on GPUs","display_name":"A model-driven partitioning and auto-tuning integrated framework for sparse matrix-vector multiplication on GPUs","publication_year":2011,"publication_date":"2011-07-18","ids":{"openalex":"https://openalex.org/W2011159963","doi":"https://doi.org/10.1145/2016741.2016744","mag":"2011159963"},"language":"en","primary_location":{"id":"doi:10.1145/2016741.2016744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016741.2016744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 TeraGrid Conference: Extreme Digital Discovery","raw_type":"proceedings-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/A5020083340","display_name":"Ping Guo","orcid":"https://orcid.org/0000-0002-7122-1084"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Guo","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101998852","display_name":"He Huang","orcid":"https://orcid.org/0000-0003-2768-6607"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Huang","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086161202","display_name":"Qichang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qichang Chen","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427863","display_name":"Liqiang Wang","orcid":"https://orcid.org/0000-0002-1265-4656"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liqiang Wang","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064569590","display_name":"En\u2010Jui Lee","orcid":"https://orcid.org/0000-0003-1545-1640"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"En-Jui Lee","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060354305","display_name":"Po Chen","orcid":"https://orcid.org/0000-0002-5148-9788"},"institutions":[{"id":"https://openalex.org/I12834331","display_name":"University of Wyoming","ror":"https://ror.org/01485tq96","country_code":"US","type":"education","lineage":["https://openalex.org/I12834331"]},{"id":"https://openalex.org/I4210116506","display_name":"Wyoming Department of Education","ror":"https://ror.org/02abxwv41","country_code":"US","type":"government","lineage":["https://openalex.org/I4210116506"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po Chen","raw_affiliation_strings":["University of Wyoming","university of Wyoming"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wyoming","institution_ids":["https://openalex.org/I4210116506","https://openalex.org/I12834331"]},{"raw_affiliation_string":"university of Wyoming","institution_ids":["https://openalex.org/I4210116506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3187,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.88687408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9973999857902527,"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/cuda","display_name":"CUDA","score":0.9431496858596802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893744707107544},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7757631540298462},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7646061182022095},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6446477174758911},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6082018613815308},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6009613871574402},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5751830339431763},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5251405239105225},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49729374051094055},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4711398482322693},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45692113041877747},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4335029423236847},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34373533725738525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08264043927192688},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07255002856254578}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9431496858596802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893744707107544},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7757631540298462},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7646061182022095},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6446477174758911},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6082018613815308},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6009613871574402},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5751830339431763},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5251405239105225},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49729374051094055},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4711398482322693},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45692113041877747},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4335029423236847},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34373533725738525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08264043927192688},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07255002856254578},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2016741.2016744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2016741.2016744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 TeraGrid Conference: Extreme Digital Discovery","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1036067696","display_name":null,"funder_award_id":"09417350930040CAREER-1054834","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1990832096","https://openalex.org/W2107483876","https://openalex.org/W2124007994","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2144511445","https://openalex.org/W2148542244","https://openalex.org/W2154118576","https://openalex.org/W2157456954","https://openalex.org/W2997945685","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2151046618","https://openalex.org/W1972148443","https://openalex.org/W1969233021","https://openalex.org/W2167646277","https://openalex.org/W2063573318","https://openalex.org/W2388314963","https://openalex.org/W3158047141","https://openalex.org/W1656096860","https://openalex.org/W2027443981","https://openalex.org/W52131579"],"abstract_inverted_index":{"Sparse":[0],"Matrix-Vector":[1],"Multiplication":[2],"(SpMV)":[3],"is":[4,111],"very":[5],"common":[6],"to":[7,24,50,71,88,91,141,146,153],"scientific":[8],"computing.":[9],"The":[10],"Graphics":[11],"Processing":[12],"Unit":[13],"(GPU)":[14],"has":[15,166],"recently":[16],"emerged":[17],"as":[18],"a":[19,84,161],"high-performance":[20],"computing":[21],"platform":[22],"due":[23],"its":[25],"massive":[26],"processing":[27],"capability.":[28],"This":[29,58],"paper":[30,59],"presents":[31],"an":[32,66],"innovative":[33],"performance-model":[34],"driven":[35],"approach":[36,159],"for":[37,176],"partitioning":[38,86,135],"sparse":[39,95,122],"matrix":[40,96,123],"into":[41,97,106],"appropriate":[42,107],"formats,":[43],"and":[44,82,102,169,182],"auto-tuning":[45,139],"configurations":[46],"of":[47,54,76,121,129],"CUDA":[48,68,78],"kernels":[49],"improve":[51],"the":[52,61,73,93,114,117,127,133,154,174],"performance":[53,69,128,148,163,171],"SpMV":[55,77],"on":[56,113,149,173],"GPUs.":[57,151],"makes":[60],"following":[62],"contributions:":[63],"(1)":[64],"Propose":[65],"empirical":[67],"model":[70],"predict":[72,89],"execution":[74],"time":[75],"kernels.":[79],"(2)":[80],"Design":[81],"implement":[83],"model-driven":[85,134],"framework":[87,140],"how":[90],"partition":[92,105],"target":[94],"one":[98],"or":[99],"more":[100],"partitions":[101],"transform":[103],"each":[104],"storage":[108,119],"format,":[109],"which":[110],"based":[112],"fact":[115],"that":[116],"different":[118],"formats":[120],"can":[124],"significantly":[125],"affect":[126],"SpMV.":[130],"(3)":[131],"Integrate":[132],"with":[136],"our":[137,158],"previous":[138],"automatically":[142],"adjust":[143],"CUDA-specific":[144],"parameters":[145],"optimize":[147],"specific":[150],"Compared":[152],"NVIDIA's":[155],"existing":[156],"implementations,":[157],"shows":[160],"substantial":[162],"improvement.":[164],"It":[165],"222%,":[167],"197%,":[168],"33%":[170],"improvement":[172],"average":[175],"CSR":[177],"vector":[178],"kernel,":[179,184],"ELL":[180],"kernel":[181],"HYB":[183],"respectively.":[185]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}