{"id":"https://openalex.org/W2170634604","doi":"https://doi.org/10.1145/1504176.1504194","title":"OpenMP to GPGPU","display_name":"OpenMP to GPGPU","publication_year":2009,"publication_date":"2009-02-14","ids":{"openalex":"https://openalex.org/W2170634604","doi":"https://doi.org/10.1145/1504176.1504194","mag":"2170634604"},"language":"en","primary_location":{"id":"doi:10.1145/1504176.1504194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","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/A5090962911","display_name":"Seyong Lee","orcid":"https://orcid.org/0000-0001-8872-4932"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyong Lee","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081601034","display_name":"Seung-Jai Min","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seung-Jai Min","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045622261","display_name":"Rudolf Eigenmann","orcid":"https://orcid.org/0000-0003-1651-827X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudolf Eigenmann","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":54.1676,"has_fulltext":false,"cited_by_count":413,"citation_normalized_percentile":{"value":0.99971618,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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":0.9940999746322632,"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":0.8977720141410828},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8914011716842651},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8416836261749268},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8026536107063293},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7758647799491882},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.49345818161964417},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.46044856309890747},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4484092891216278},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43379196524620056},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30363786220550537},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23147815465927124},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.19026604294776917}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8977720141410828},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8914011716842651},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8416836261749268},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8026536107063293},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7758647799491882},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.49345818161964417},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.46044856309890747},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4484092891216278},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43379196524620056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30363786220550537},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23147815465927124},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.19026604294776917}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1504176.1504194","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1504176.1504194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1340","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/347","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1502558230","https://openalex.org/W1517684295","https://openalex.org/W1532125006","https://openalex.org/W1537323515","https://openalex.org/W1574021171","https://openalex.org/W1977043846","https://openalex.org/W1985410827","https://openalex.org/W1992851788","https://openalex.org/W1998198109","https://openalex.org/W2015789401","https://openalex.org/W2022711417","https://openalex.org/W2035080386","https://openalex.org/W2083056254","https://openalex.org/W2108792719","https://openalex.org/W2135736783","https://openalex.org/W2146606012","https://openalex.org/W2153492376","https://openalex.org/W2264086856"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W2778498407","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112"],"abstract_inverted_index":{"GPGPUs":[0,30],"have":[1,78],"recently":[2],"emerged":[3],"as":[4],"powerful":[5],"vehicles":[6],"for":[7,26,42],"general-purpose":[8],"high-performance":[9],"computing.":[10],"Although":[11],"a":[12,39],"new":[13],"Compute":[14],"Unified":[15],"Device":[16],"Architecture":[17],"(CUDA)":[18],"programming":[19,29],"model":[20],"from":[21,97],"NVIDIA":[22],"offers":[23],"improved":[24],"programmability":[25,63],"general":[27],"computing,":[28],"is":[31,59],"still":[32],"complex":[33],"and":[34,64,102,104,111,118,126],"error-prone.":[35],"This":[36],"paper":[37],"presents":[38],"compiler":[40],"framework":[41],"automatic":[43],"source-to-source":[44],"translation":[45,58,140],"of":[46,56,133],"standard":[47],"OpenMP":[48,67,107],"applications":[49,68],"into":[50],"CUDA-based":[51],"GPGPU":[52],"applications.":[53],"The":[54],"goal":[55],"this":[57,75],"to":[60,70,91,130,135,142],"further":[61],"improve":[62],"make":[65],"existing":[66],"amenable":[69],"execution":[71],"on":[72,123],"GPGPUs.":[73],"In":[74],"paper,":[76],"we":[77],"identified":[79],"several":[80],"key":[81],"transformation":[82],"techniques,":[83],"which":[84],"enable":[85],"efficient":[86],"GPU":[87],"global":[88],"memory":[89],"access,":[90],"achieve":[92],"high":[93],"performance.":[94],"Experimental":[95],"results":[96],"two":[98,105],"important":[99],"kernels":[100],"(JACOBI":[101],"SPMUL)":[103],"NAS":[106],"Parallel":[108],"Benchmarks":[109],"(EP":[110],"CG)":[112],"show":[113],"that":[114],"the":[115,138],"described":[116],"translator":[117],"compile-time":[119],"optimizations":[120],"work":[121],"well":[122],"both":[124],"regular":[125],"irregular":[127],"applications,":[128],"leading":[129],"performance":[131],"improvements":[132],"up":[134],"50X":[136],"over":[137,144],"unoptimized":[139],"(up":[141],"328X":[143],"serial).":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":35},{"year":2013,"cited_by_count":64},{"year":2012,"cited_by_count":69}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2016-06-24T00:00:00"}