{"id":"https://openalex.org/W171055650","doi":"https://doi.org/10.6092/polito/porto/2506355","title":"General Purpose Computation on Graphics Processing Units Using OpenCL","display_name":"General Purpose Computation on Graphics Processing Units Using OpenCL","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W171055650","doi":"https://doi.org/10.6092/polito/porto/2506355","mag":"171055650"},"language":"en","primary_location":{"id":"pmh:oai:porto.polito.it:2506355","is_oa":true,"landing_page_url":"http://porto.polito.it/2506355/","pdf_url":"http://porto.polito.it/2506355/","source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://porto.polito.it/2506355/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063615079","display_name":"Fiaz Gul Khan","orcid":"https://orcid.org/0000-0003-1220-0002"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Khan, Fiaz Gul","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5063615079"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4944,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74198016,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11786","display_name":"Geomagnetism and Paleomagnetism Studies","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9488999843597412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907314300537109},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6846862435340881},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6751020550727844},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6165318489074707},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5107834339141846},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5023086071014404},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4649926722049713},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4314623177051544},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42082133889198303},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.18510806560516357},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18003177642822266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907314300537109},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6846862435340881},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6751020550727844},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6165318489074707},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5107834339141846},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5023086071014404},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4649926722049713},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4314623177051544},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42082133889198303},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.18510806560516357},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18003177642822266},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:porto.polito.it:2506355","is_oa":true,"landing_page_url":"http://porto.polito.it/2506355/","pdf_url":"http://porto.polito.it/2506355/","source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"doi:10.6092/polito/porto/2506355","is_oa":true,"landing_page_url":"https://doi.org/10.6092/polito/porto/2506355","pdf_url":null,"source":{"id":"https://openalex.org/S7407050979","display_name":"Politecnico di Torino","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:porto.polito.it:2506355","is_oa":true,"landing_page_url":"http://porto.polito.it/2506355/","pdf_url":"http://porto.polito.it/2506355/","source":{"id":"https://openalex.org/S4306402038","display_name":"PORTO Publications Open Repository TOrino (Politecnico di Torino)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177477856","host_organization_name":"Politecnico di Torino","host_organization_lineage":["https://openalex.org/I177477856"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W171055650.pdf","grobid_xml":"https://content.openalex.org/works/W171055650.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2161993152","https://openalex.org/W1587622926","https://openalex.org/W2060451781","https://openalex.org/W2254642858","https://openalex.org/W2313675904","https://openalex.org/W2079342791","https://openalex.org/W2406264764","https://openalex.org/W2386968296","https://openalex.org/W2181557959","https://openalex.org/W3193785196","https://openalex.org/W3158834397","https://openalex.org/W1991763756","https://openalex.org/W2294001614","https://openalex.org/W2293571750","https://openalex.org/W2244491995","https://openalex.org/W1992299697","https://openalex.org/W2090498768","https://openalex.org/W2129757772","https://openalex.org/W2188083286","https://openalex.org/W2187537688"],"abstract_inverted_index":{"Computational":[0],"Science":[1],"has":[2,548],"emerged":[3],"as":[4,61,116,130,207,228,379],"a":[5,149,202,353,415,532,582],"third":[6],"pillar":[7],"of":[8,50,84,96,104,138,156,161,193,204,264,293,408,430,433,444,473,524,531,541,561],"science":[9],"along":[10],"with":[11,74,101,159,282,339,428,565],"theory":[12],"and":[13,26,35,40,78,106,112,118,145,178,191,214,342,388,410,515,572,577,580],"experiment,":[14],"where":[15,153],"the":[16,45,48,94,102,121,136,154,170,174,250,262,306,317,334,346,365,369,400,406,431,441,467,522,539,559],"parallelization":[17],"for":[18,55,124,166,225,245,270,279,290,296,323,356,535,544],"scientific":[19],"computing":[20,58,71,87,547],"is":[21,98,169,180,199,286,303,505],"promised":[22],"by":[23,305,439],"different":[24,125,357,562,575],"shared":[25],"distributed":[27],"memory":[28,381,392,437],"architectures":[29,579],"such":[30,115,129,206,378],"as,":[31],"super-computer":[32],"systems,":[33,38,512,514],"grid":[34],"cluster":[36],"based":[37,320,460],"multi-core":[39],"multiprocessor":[41],"systems":[42,72,295],"etc.":[43,217,398],"In":[44,133,360,399,491,519,553],"recent":[46],"years":[47],"use":[49,109],"GPUs":[51,82,122,366,425,434,587],"(Graphic":[52],"Processing":[53],"Units)":[54],"General":[56],"purpose":[57,546],"commonly":[59],"known":[60],"GPGPU":[62],"made":[63,120,328],"it":[64,179,229,285,329,350],"an":[65,287,454,525],"exciting":[66],"addition":[67],"to":[68,76,108,201,254,331,362,372,403,567],"high":[69],"performance":[70,79],"(HPC)":[73],"respect":[75,566],"price":[77],"ratio.":[80],"Current":[81],"consist":[83],"several":[85],"hundred":[86],"cores":[88],"arranged":[89],"in":[90,221,240,345,483,487,507],"streaming":[91],"multi-processors":[92],"so":[93],"degree":[95],"parallelism":[97,409],"promising.":[99],"Moreover":[100,349],"development":[103,263],"new":[105,583],"easy":[107],"interfacing":[110],"tools":[111],"programming":[113,227,292],"languages":[114],"OpenCL":[117,278,319],"CUDA":[119],"suitable":[123,224],"computation":[126,151,474],"demanding":[127],"applications":[128,509],"micromagnetic":[131,134,219,246,271,468],"simulations.":[132,518],"simulations,":[135],"study":[137,190],"magnetic":[139,208,215],"behavior":[140,195],"at":[141,184,196],"very":[142,481],"small":[143],"time":[144,186],"space":[146],"scale":[147],"demands":[148],"huge":[150],"time,":[152,177,569],"calculation":[155,302,326],"magnetostatic":[157,267,300,324,417],"field":[158,268,301,325,347,418],"complexity":[160],"O(Nlog(N))":[162],"using":[163,277],"FFT":[164],"algorithm":[165,534],"discrete":[167,516],"convolution":[168],"main":[171],"contribution":[172],"towards":[173],"whole":[175],"simulation":[176],"computed":[181],"many":[182,374,429,508],"times":[183],"each":[185],"step":[187,402],"interval.":[188],"This":[189],"observation":[192],"magnetization":[194],"sub-nanosecond":[197],"time-scales":[198],"crucial":[200],"number":[203],"areas":[205],"sensors,":[209],"non":[210],"volatile":[211],"storage":[212],"devices":[213],"nanowires":[216],"Since":[218],"codes":[220],"general":[222,545],"are":[223],"parallel":[226,266,291,367,416,461,492],"can":[230,238,478],"be":[231,479],"easily":[232],"divided":[233],"into":[234],"independent":[235],"parts":[236,253],"which":[237,327,465,470],"run":[239],"parallel,":[241],"therefore":[242],"current":[243],"trend":[244],"code":[247,370],"concerns":[248],"shifting":[249],"computationally":[251],"intensive":[252],"GPUs.":[255,274,359,422,448,490,501],"My":[256],"PhD":[257],"work":[258,555],"mainly":[259],"focuses":[260],"on":[261,273,420,446,463,475,489,496,500,529,574,586],"highly":[265],"solver":[269,419],"simulators":[272],"I":[275,412,493],"am":[276],"GPU":[280,387,390,450,576],"implementation,":[281],"consideration":[283],"that":[284],"open":[288],"standard":[289],"heterogeneous":[294],"cross":[297],"platform.":[298],"The":[299,449],"dominated":[304],"multidimensional":[307],"FFTs":[308],"(Fast":[309],"Fourier":[310],"Transform)":[311],"computation.":[312],"Therefore":[313],"i":[314,556],"have":[315,413,452,557],"developed":[316,414],"specialized":[318],"3D-FFT":[321],"library":[322],"possible":[330],"fully":[332,363],"exploit":[333],"zero":[335],"padded":[336],"input":[337],"data":[338,383],"out":[340],"transposition":[341],"symmetries":[343],"inherent":[344],"calculation.":[348],"also":[351,494],"provides":[352],"common":[354],"interface":[355],"vendors'":[358],"order":[361],"utilize":[364],"architecture":[368],"needs":[371],"handle":[373],"hardware":[375],"specific":[376],"technicalities":[377],"coalesced":[380],"access,":[382],"transfer":[384],"overhead":[385],"between":[386],"CPU,":[389,464],"global":[391],"utilization,":[393],"arithmetic":[394],"computation,":[395],"batch":[396],"execution":[397],"second":[401],"further":[404],"increase":[405],"level":[407],"performance,":[411],"multiple":[421,424,445],"Utilizing":[423],"avoids":[426],"dealing":[427],"limitations":[432],"(e.g.,":[435],"on-chip":[436],"resources)":[438],"exploiting":[440],"combined":[442],"resources":[443],"board":[447],"implementation":[451,462],"shown":[453],"impressive":[455],"speedup":[456,573],"against":[457],"equivalent":[458],"OpenMp":[459],"means":[466],"simulations":[469],"require":[471],"weeks":[472],"CPU":[476,578],"now":[477],"performed":[480],"fast":[482],"hours":[484],"or":[485],"even":[486],"minutes":[488],"worked":[495],"ordered":[497],"queue":[498,503],"management":[499,504],"Ordered":[502],"used":[506],"including":[510],"real-time":[511],"operating":[513],"event":[517],"most":[520],"cases,":[521],"efficiency":[523],"application":[526],"itself":[527],"depends":[528],"usage":[530,540],"sorting":[533,551,563,568,570,584],"priority":[536],"queues.":[537],"Lately,":[538],"graphic":[542],"cards":[543],"again":[549],"revisited":[550],"algorithms.":[552],"this":[554],"presented":[558],"analysis":[560],"algorithms":[564],"rate":[571],"provided":[581],"technique":[585]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
