{"id":"https://openalex.org/W2748714099","doi":"https://doi.org/10.1109/se-hpccse.2016.012","title":"Code Complexity versus Performance for GPU-accelerated Scientific Applications","display_name":"Code Complexity versus Performance for GPU-accelerated Scientific Applications","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2748714099","doi":"https://doi.org/10.1109/se-hpccse.2016.012","mag":"2748714099"},"language":"en","primary_location":{"id":"doi:10.1109/se-hpccse.2016.012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/se-hpccse.2016.012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Fourth International Workshop on Software Engineering for High Performance Computing in Computational Science and Engineering (SE-HPCCSE)","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5071582526","display_name":"A Wk. Umayanganie Munipala","orcid":null},"institutions":[{"id":"https://openalex.org/I164936912","display_name":"The University of Texas at El Paso","ror":"https://ror.org/04d5vba33","country_code":"US","type":"education","lineage":["https://openalex.org/I164936912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A WK. Umayanganie Munipala","raw_affiliation_strings":["University of Texas at El Paso, 500 West University Avenue, El Paso, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at El Paso, 500 West University Avenue, El Paso, TX","institution_ids":["https://openalex.org/I164936912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041037945","display_name":"Shirley Moore","orcid":"https://orcid.org/0009-0009-1351-2797"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirley V. Moore","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.989799976348877,"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":0.989799976348877,"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":0.9865999817848206,"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":0.9836000204086304,"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/computer-science","display_name":"Computer science","score":0.7298641800880432},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.686859667301178},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6294412612915039},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.463161826133728},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3301214575767517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.315234899520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7298641800880432},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.686859667301178},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6294412612915039},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.463161826133728},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3301214575767517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.315234899520874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/se-hpccse.2016.012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/se-hpccse.2016.012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Fourth International Workshop on Software Engineering for High Performance Computing in Computational Science and Engineering (SE-HPCCSE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2115140794","https://openalex.org/W2041120224","https://openalex.org/W1504320321","https://openalex.org/W2067902980","https://openalex.org/W2548529098","https://openalex.org/W4231937131","https://openalex.org/W4312275919","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W2056396287"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"Graphics":[4],"Processing":[5],"Units":[6],"(GPUs)":[7],"are":[8,255,274],"becoming":[9],"widely":[10],"used":[11],"as":[12,31,70],"parallel":[13],"accelerators":[14],"in":[15,43,65],"high-performance":[16],"computing.":[17],"GPU":[18,253],"programming":[19,28,38],"until":[20],"recently,":[21],"has":[22,40],"been":[23,41],"done":[24],"by":[25],"using":[26,155],"low-level":[27],"models":[29],"such":[30,69],"CUDA":[32,132,194,220],"and":[33,73,95,100,120,134,137,142,152,176,187,195,221,247,264,269,272],"OpenCL.":[34],"The":[35,219],"directive-based":[36],"OpenACC":[37,101,207,237],"model":[39],"growing":[42],"popularity":[44],"due":[45],"to":[46,60,77,83,91,181],"its":[47],"higher":[48],"level":[49],"of":[50,97,110,149,179,202,252,266],"abstraction.":[51],"This":[52],"technique,":[53],"which":[54],"uses":[55],"\u201cdirective\u201d":[56],"or":[57],"\u201cpragma\u201d":[58],"statements":[59],"annotate":[61],"source":[62,147],"code":[63,81,93,150,203,238],"written":[64],"traditional":[66],"high-level":[67],"languages":[68],"Fortran,":[71],"C,":[72,131,133],"C++,":[74,140],"is":[75,215,230,239],"intended":[76],"allow":[78],"a":[79,232],"single":[80],"base":[82],"work":[84],"across":[85],"multiple":[86],"computational":[87],"platforms.":[88],"We":[89,162,190,241],"attempt":[90],"compare":[92],"complexity":[94,154,214,251],"performance":[96],"CUDA,":[98,141],"OpenCL,":[99],"implementations":[102,197,208,223],"for":[103,249],"three":[104],"benchmark":[105],"codes":[106,136],"-":[107],"the":[108,115,121,125,129,138,156,164,170,193,205,211,236,244,262,267],"Game":[109],"Life":[111],"(GOL)":[112],"example":[113],"code,":[114],"LULESH":[116,139],"hydrodynamics":[117],"proxy":[118],"application,":[119],"CloverLeaf":[122,171],"mini-app":[123],"from":[124],"Mantevo":[126],"suite":[127],"For":[128],"GOL":[130],"OpenCL":[135,143,196,222],"codes,":[144,268],"we":[145],"measured":[146,212],"lines":[148,201],"(SLOC)":[151],"cyclomatic":[153,183,213],"Oxbow":[157],"toolkit":[158],"static":[159],"analysis":[160],"tools.":[161],"ran":[163],"commercial":[165],"McCabe":[166],"IQ":[167],"tool":[168],"on":[169],"Fortran90,":[172],"Fortran90":[173],"+":[174],"OpenACC,":[175],"Fortran":[177],"portion":[178],"CloverLeaf_CUDA":[180],"measure":[182],"complexity,":[184,186],"design":[185],"essential":[188],"complexity.":[189],"found":[191],"that":[192,210,243,270],"have":[198,225],"significantly":[199],"more":[200],"than":[204],"corresponding":[206],"but":[209,228],"not":[216,231,260],"always":[217],"higher.":[218],"generally":[224],"better":[226],"performance,":[227],"there":[229],"drastic":[233],"difference":[234],"if":[235],"optimized.":[240],"conclude":[242],"available":[245],"metrics":[246],"tools":[248],"measuring":[250],"programs":[254],"inadequate,":[256],"since":[257],"they":[258],"do":[259],"quantify":[261],"portability":[263],"maintainability":[265],"specialization":[271],"extensions":[273],"needed.":[275]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}