{"id":"https://openalex.org/W4407741114","doi":"https://doi.org/10.3233/978-1-61499-621-7-217","title":"Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems","display_name":"Harnessing CUDA Dynamic Parallelism for the Solution of Sparse Linear Systems","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W4407741114","doi":"https://doi.org/10.3233/978-1-61499-621-7-217"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-621-7-217","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-217","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5116328294","display_name":"Aliaga Jos eacute","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Aliaga José","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116328295","display_name":"Davidovi cacute Davor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davidović Davor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108124957","display_name":"P eacute rez Joaqu iacute n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pérez Joaquín","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5116328296","display_name":"Quintana-Ort iacute Enrique S.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quintana-Ortí Enrique S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5116328294"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.448,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71175373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9692999720573425,"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":0.9692999720573425,"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":0.9527000188827515,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9384999871253967,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8804985880851746},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.7712886333465576},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7542334794998169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133126258850098},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.377856969833374}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8804985880851746},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.7712886333465576},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7542334794998169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133126258850098},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.377856969833374}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/978-1-61499-621-7-217","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-217","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2023505575","https://openalex.org/W3189307731","https://openalex.org/W1595672120","https://openalex.org/W1428699136","https://openalex.org/W4230999561","https://openalex.org/W2949962288"],"abstract_inverted_index":{"We":[0],"leverage":[1],"CUDA":[2,51,57],"dynamic":[3],"parallelism":[4],"to":[5],"reduce":[6],"execution":[7,69,82],"time":[8],"while":[9,67],"significantly":[10],"reducing":[11],"energy":[12],"consumption":[13],"of":[14,24,36,47,70,106],"the":[15,21,42,45,68,71,76,81,104,107],"Conjugate":[16],"Gradient":[17],"(CG)":[18],"method":[19],"for":[20],"iterative":[22],"solution":[23],"sparse":[25],"linear":[26],"systems":[27],"on":[28,75,87],"graphics":[29],"processing":[30],"units":[31],"(GPUs).":[32],"Our":[33,85],"new":[34,108],"implementation":[35],"this":[37],"solver":[38,72],"is":[39,83],"launched":[40],"from":[41],"CPU":[43,60,96],"in":[44],"form":[46],"a":[48,88],"single":[49],"“parent”":[50],"kernel,":[52],"which":[53],"invokes":[54],"other":[55,65],"“child”":[56],"kernels.":[58],"The":[59],"can":[61],"then":[62],"continue":[63],"with":[64,91],"work":[66],"proceeds":[73],"asynchronously":[74],"GPU,":[77],"or":[78],"block":[79],"until":[80],"completed.":[84],"experiments":[86],"server":[89],"equipped":[90],"an":[92,98],"Intel":[93],"Core":[94],"i7-3770K":[95],"and":[97],"NVIDIA":[99],"“Kepler”":[100],"K20c":[101],"GPU":[102],"illustrate":[103],"benefits":[105],"CG":[109],"solver.":[110]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}