{"id":"https://openalex.org/W2588313843","doi":"https://doi.org/10.1145/3038228.3038240","title":"Parallel CCD++ on GPU for Matrix Factorization","display_name":"Parallel CCD++ on GPU for Matrix Factorization","publication_year":2017,"publication_date":"2017-02-04","ids":{"openalex":"https://openalex.org/W2588313843","doi":"https://doi.org/10.1145/3038228.3038240","mag":"2588313843"},"language":"en","primary_location":{"id":"doi:10.1145/3038228.3038240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","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/A5063948428","display_name":"Israt Nisa","orcid":"https://orcid.org/0000-0001-5022-5716"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Israt Nisa","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039567585","display_name":"Rakshith Kunchum","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakshith Kunchum","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063948428"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.4564,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89128626,"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":"73","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8096210956573486},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6550449132919312},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6160503625869751},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5906191468238831},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5589554905891418},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5466887354850769},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5153836011886597},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4580167829990387},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4524478018283844},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38558295369148254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8096210956573486},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6550449132919312},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6160503625869751},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5906191468238831},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5589554905891418},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5466887354850769},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5153836011886597},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4580167829990387},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4524478018283844},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38558295369148254},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3038228.3038240","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":28,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1511814458","https://openalex.org/W1540764732","https://openalex.org/W1919585499","https://openalex.org/W1980147176","https://openalex.org/W2020098476","https://openalex.org/W2022712430","https://openalex.org/W2026034143","https://openalex.org/W2054141820","https://openalex.org/W2063468305","https://openalex.org/W2076566842","https://openalex.org/W2080371694","https://openalex.org/W2091825929","https://openalex.org/W2108712612","https://openalex.org/W2112284959","https://openalex.org/W2121966774","https://openalex.org/W2124187902","https://openalex.org/W2125996677","https://openalex.org/W2142466236","https://openalex.org/W2143822352","https://openalex.org/W2146682077","https://openalex.org/W2149814409","https://openalex.org/W2155959613","https://openalex.org/W2165966284","https://openalex.org/W2170551306","https://openalex.org/W2297086932","https://openalex.org/W2951781666","https://openalex.org/W2952033860"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2052993554","https://openalex.org/W1973739845","https://openalex.org/W119752240","https://openalex.org/W2046125858","https://openalex.org/W2030992542","https://openalex.org/W2898722594","https://openalex.org/W2113856999","https://openalex.org/W4391266752","https://openalex.org/W133838137"],"abstract_inverted_index":{"Matrix":[0],"factorization":[1,22,132],"of":[2,34,57,67,77,92,120,130],"an":[3,41],"incomplete":[4],"matrix":[5,21,131],"is":[6,109],"useful":[7],"in":[8],"applications":[9],"such":[10],"as":[11,40,122,124],"recommender":[12,24],"systems.":[13],"Several":[14],"iterative":[15],"algorithms":[16],"have":[17],"been":[18],"proposed":[19],"for":[20,23,44,59],"systems,":[25],"including":[26],"Cyclic":[27],"Coordinate":[28],"Descent":[29],"(CCD).":[30],"Recently":[31],"a":[32,60,83],"variant":[33],"CCD":[35],"called":[36],"CCD++":[37,58,93,121],"was":[38],"developed":[39],"attractive":[42],"algorithm":[43,108],"parallel":[45],"implementation":[46,91,119,129],"on":[47],"multicore":[48,118],"processors.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,86],"address":[54],"the":[55,65,89,115,125],"parallelization":[56],"GPU.":[61],"Key":[62],"considerations":[63],"are":[64],"reduction":[66],"data":[68],"volume":[69],"transferred":[70],"from/to":[71],"GPU":[72,90,128],"global":[73],"memory":[74],"and":[75,97],"minimization":[76],"intra-warp":[78],"load":[79],"imbalance.":[80],"Starting":[81],"with":[82],"base":[84],"implementation,":[85],"successively":[87],"improve":[88],"using":[94,99],"loop":[95],"fusion":[96],"tiling,":[98],"performance":[100],"insights":[101],"from":[102],"hardware":[103],"counter":[104],"data.":[105],"The":[106],"resulting":[107],"shown":[110],"to":[111],"be":[112],"faster":[113],"than":[114],"best":[116,126],"reported":[117,127],"well":[123],"(using":[133],"ALS,":[134],"Alternating":[135],"Least":[136],"Squares).":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}