{"id":"https://openalex.org/W4243205343","doi":"https://doi.org/10.1109/cgo.2015.7054194","title":"Optimizing and auto-tuning scale-free sparse matrix-vector multiplication on Intel Xeon Phi","display_name":"Optimizing and auto-tuning scale-free sparse matrix-vector multiplication on Intel Xeon Phi","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W4243205343","doi":"https://doi.org/10.1109/cgo.2015.7054194"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2015.7054194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5103180941","display_name":"Wai Teng Tang","orcid":"https://orcid.org/0000-0002-6553-1270"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wai Teng Tang","raw_affiliation_strings":["Institute of High Performance Computing, Technology and Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103214318","display_name":"Rongxuan Zhao","orcid":"https://orcid.org/0009-0001-9705-3701"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruizhe Zhao","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103114808","display_name":"Mian Lu","orcid":"https://orcid.org/0009-0002-4853-8881"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mian Lu","raw_affiliation_strings":["Institute of High Performance Computing, Technology and Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Peking University, Beijing, Beijing, CN"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, CN","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088829523","display_name":"Huynh Phung Huyng","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huynh Phung Huyng","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012994624","display_name":"Xibai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibai Li","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103180941"],"corresponding_institution_ids":["https://openalex.org/I3004594783"],"apc_list":null,"apc_paid":null,"fwci":4.5218,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95016671,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"145"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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":0.9973999857902527,"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/xeon-phi","display_name":"Xeon Phi","score":0.8878813982009888},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8157005906105042},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7528891563415527},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7200281023979187},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.616253137588501},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5990586876869202},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5109221339225769},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5058829188346863},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4205703139305115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12278386950492859}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8878813982009888},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157005906105042},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7528891563415527},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7200281023979187},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.616253137588501},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5990586876869202},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5109221339225769},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5058829188346863},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4205703139305115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12278386950492859},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2015.7054194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":23,"referenced_works":["https://openalex.org/W348433680","https://openalex.org/W1482680420","https://openalex.org/W1506342804","https://openalex.org/W1594498663","https://openalex.org/W1653630692","https://openalex.org/W1776498962","https://openalex.org/W1854214752","https://openalex.org/W1965551736","https://openalex.org/W1971343078","https://openalex.org/W1987840949","https://openalex.org/W1990832096","https://openalex.org/W2008620264","https://openalex.org/W2035080386","https://openalex.org/W2072806558","https://openalex.org/W2093053744","https://openalex.org/W2099625934","https://openalex.org/W2114977680","https://openalex.org/W2128853364","https://openalex.org/W4295539146","https://openalex.org/W6611841979","https://openalex.org/W6635425727","https://openalex.org/W6636930873","https://openalex.org/W6639055396"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W4252450863","https://openalex.org/W2467043670","https://openalex.org/W2085105049","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458","https://openalex.org/W1981810806","https://openalex.org/W2279642117"],"abstract_inverted_index":{"Recently,":[0],"the":[1,38,59,103,108],"Intel":[2,137],"Xeon":[3,39],"Phi":[4,40],"coprocessor":[5],"has":[6],"received":[7],"increasing":[8],"attention":[9],"in":[10,52,58],"high":[11],"performance":[12,105,117],"computing":[13],"due":[14],"to":[15,93,120],"its":[16,44,122],"simple":[17],"programming":[18],"model":[19],"and":[20,42,66,88,98],"highly":[21],"parallel":[22],"architecture.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,113],"implement":[28],"sparse":[29,47],"matrix":[30],"vector":[31],"multiplication":[32],"(SpMV)":[33],"for":[34,139],"scale-free":[35,144],"matrices":[36,48],"on":[37,107],"architecture":[41],"optimize":[43],"performance.":[45,101],"Scale-free":[46],"are":[49],"widely":[50],"used":[51],"various":[53],"application":[54],"domains,":[55],"such":[56],"as":[57],"study":[60],"of":[61,110,143],"social":[62],"networks,":[63],"gene":[64],"networks":[65],"web":[67],"graphs.":[68],"We":[69],"propose":[70],"a":[71,116,140],"novel":[72],"SpMV":[73,81,129],"format":[74],"called":[75],"vectorized":[76,89],"hybrid":[77],"COO+CSR":[78],"(VHCC).":[79],"Our":[80],"implementation":[82,130],"employs":[83],"2D":[84],"jagged":[85],"partitioning,":[86],"tiling":[87],"prefix":[90],"sum":[91],"computations":[92],"improve":[94],"hardware":[95],"resource":[96],"utilization,":[97],"thus":[99],"overall":[100],"As":[102],"achieved":[104],"depends":[106],"number":[109],"vertical":[111],"panels,":[112],"also":[114],"develop":[115],"tuning":[118],"method":[119],"guide":[121],"selection.":[123],"Experimental":[124],"results":[125],"demonstrate":[126],"that":[127],"our":[128],"achieves":[131],"an":[132],"average":[133],"3\u00d7":[134],"speedup":[135],"over":[136],"MKL":[138],"wide":[141],"range":[142],"matrices.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
