{"id":"https://openalex.org/W1969816979","doi":"https://doi.org/10.1145/2636228.2636236","title":"Native offload of Haskell repa programs to integrated GPUs","display_name":"Native offload of Haskell repa programs to integrated GPUs","publication_year":2014,"publication_date":"2014-09-03","ids":{"openalex":"https://openalex.org/W1969816979","doi":"https://doi.org/10.1145/2636228.2636236","mag":"1969816979"},"language":"en","primary_location":{"id":"doi:10.1145/2636228.2636236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2636228.2636236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGPLAN workshop on Functional high-performance computing","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/A5100368947","display_name":"Hai Liu","orcid":"https://orcid.org/0000-0003-1365-2940"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hai Liu","raw_affiliation_strings":["Intel Labs, Hillsboro, OR, USA","[Intel Labs, Hillsboro, OR, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"[Intel Labs, Hillsboro, OR, USA]","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019761321","display_name":"Laurence E. Day","orcid":null},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Laurence E. Day","raw_affiliation_strings":["The University of Nottingham, Nottingham, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Nottingham, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071801109","display_name":"Neal Glew","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neal Glew","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103271482","display_name":"Todd A. Anderson","orcid":"https://orcid.org/0000-0002-5739-6320"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd A. Anderson","raw_affiliation_strings":["Intel Labs, Hillsboro, OR, USA","[Intel Labs, Hillsboro, OR, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"[Intel Labs, Hillsboro, OR, USA]","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102819808","display_name":"Rajkishore Barik","orcid":"https://orcid.org/0000-0003-4779-1391"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkishore Barik","raw_affiliation_strings":["Intel Labs, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100368947"],"corresponding_institution_ids":["https://openalex.org/I1343180700"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05421533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9110483527183533},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.842029869556427},{"id":"https://openalex.org/keywords/haskell","display_name":"Haskell","score":0.8127400875091553},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.758832573890686},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7169390916824341},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.659156858921051},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6384871006011963},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5660033226013184},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4646083414554596},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.4610788822174072},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4513579308986664},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.41676026582717896},{"id":"https://openalex.org/keywords/functional-programming","display_name":"Functional programming","score":0.36170312762260437},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2921736538410187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9110483527183533},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.842029869556427},{"id":"https://openalex.org/C2780624054","wikidata":"https://www.wikidata.org/wiki/Q34010","display_name":"Haskell","level":3,"score":0.8127400875091553},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.758832573890686},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7169390916824341},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.659156858921051},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6384871006011963},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5660033226013184},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4646083414554596},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.4610788822174072},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4513579308986664},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.41676026582717896},{"id":"https://openalex.org/C42383842","wikidata":"https://www.wikidata.org/wiki/Q193076","display_name":"Functional programming","level":2,"score":0.36170312762260437},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2921736538410187},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2636228.2636236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2636228.2636236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGPLAN workshop on Functional high-performance computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W55870094","https://openalex.org/W1502641600","https://openalex.org/W1593775747","https://openalex.org/W1972151859","https://openalex.org/W1995535937","https://openalex.org/W1996060755","https://openalex.org/W2043416466","https://openalex.org/W2083310717","https://openalex.org/W2091589449","https://openalex.org/W2094413750","https://openalex.org/W2097824307","https://openalex.org/W2104958979","https://openalex.org/W2105463364","https://openalex.org/W2107032586","https://openalex.org/W2130179171","https://openalex.org/W2139626883","https://openalex.org/W2148599839","https://openalex.org/W2207795035","https://openalex.org/W2259172674","https://openalex.org/W2561675875","https://openalex.org/W3138798301","https://openalex.org/W4231380462"],"related_works":["https://openalex.org/W2058003313","https://openalex.org/W2402757940","https://openalex.org/W2112263414","https://openalex.org/W3004782279","https://openalex.org/W1602185604","https://openalex.org/W2109776807","https://openalex.org/W2028779182","https://openalex.org/W4242678340","https://openalex.org/W2140654465","https://openalex.org/W2183725039"],"abstract_inverted_index":{"In":[0,202],"light":[1],"of":[2,85,121,123,189],"recent":[3],"hardware":[4],"advances,":[5],"general-purpose":[6],"computing":[7],"on":[8,174,187,199,235],"graphics":[9],"processing":[10],"units":[11],"(GPGPU)":[12],"is":[13,79],"becoming":[14],"increasingly":[15],"commonplace,":[16],"and":[17,53,106,192,231,243],"needs":[18],"novel":[19],"programming":[20,35,40],"models":[21],"due":[22],"to":[23,34,43,65,80,92,101,137,141,156,195,213,216,220,239,247],"GPUs'":[24],"radically":[25],"different":[26,241],"architecture.":[27],"For":[28],"the":[29,86,124,130,142,147,160,181,185,196,225,233],"most":[30],"part,":[31],"existing":[32],"approaches":[33,105],"GPUs":[36],"within":[37,49,62],"a":[38,45,50,56,82,111,118,134,139],"high-level":[39],"language":[41,47,88],"choose":[42],"embed":[44],"domain-specific":[46],"(DSL)":[48],"host":[51,87],"metalanguage":[52],"then":[54],"implement":[55,221],"compiler":[57],"that":[58,63,222],"maps":[59],"programs":[60],"written":[61],"DSL":[64],"code":[66],"in":[67,113,224],"low-level":[68],"languages":[69],"such":[70],"as":[71,146],"OpenCL":[72,157,249],"or":[73],"CUDA.":[74],"An":[75],"alternative,":[76],"underexplored,":[77],"approach":[78,234],"compile":[81,154],"restricted":[83],"subset":[84],"itself":[89],"directly":[90],"down":[91],"OpenCL/CUDA.":[93],"We":[94,168,179],"believe":[95],"more":[96],"research":[97],"should":[98],"be":[99],"done":[100],"compare":[102],"these":[103],"two":[104,200,240],"their":[107],"relative":[108],"merits.":[109],"As":[110,144],"step":[112],"this":[114,203],"direction,":[115],"we":[116,128,153,205],"implemented":[117],"quick":[119],"proof":[120],"concept":[122],"alternative":[125],"approach.":[126],"Specifically,":[127],"extend":[129,214],"Repa":[131,215],"library":[132],"with":[133],"computeG":[135],"function":[136],"offload":[138,208],"computation":[140,149],"GPU.":[143,178],"long":[145],"requested":[148],"meets":[150],"certain":[151],"restrictions,":[152],"it":[155],"2.0":[158],"using":[159],"recently":[161],"added":[162],"feature":[163],"for":[164,210,244],"shared":[165],"virtual":[166],"memory.":[167],"can":[169],"successfully":[170],"run":[171],"nine":[172,236],"benchmarks":[173],"an":[175,207],"Intel":[176,226],"integrated":[177],"obtain":[180],"expected":[182,197],"performance":[183,198],"from":[184],"GPU":[186],"six":[188],"those":[190],"benchmarks,":[191,237],"are":[193],"close":[194],"more.":[201],"paper,":[204],"describe":[206],"primitive":[209,223],"Haskell,":[211],"how":[212,219],"use":[217],"it,":[218],"Labs":[227],"Haskell":[228],"Research":[229],"Compiler,":[230],"evaluate":[232],"comparing":[238],"CPUs,":[242],"one":[245],"benchmark":[246],"hand-written":[248],"code.":[250]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}