{"id":"https://openalex.org/W2402119390","doi":"https://doi.org/10.1109/hpcsim.2016.7568385","title":"ImageCL: An image processing language for performance portability on heterogeneous systems","display_name":"ImageCL: An image processing language for performance portability on heterogeneous systems","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2402119390","doi":"https://doi.org/10.1109/hpcsim.2016.7568385","mag":"2402119390"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2016.7568385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing & Simulation (HPCS)","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/A5033903615","display_name":"Thomas L. Falch","orcid":"https://orcid.org/0000-0001-8498-4825"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas L. Falch","raw_affiliation_strings":["Dept. of Comp. and Info. Science, University of Texasat Austin, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comp. and Info. Science, University of Texasat Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045535996","display_name":"Anne C. Elster","orcid":"https://orcid.org/0000-0002-7087-6193"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anne C. Elster","raw_affiliation_strings":["Dept. of Comp. and Info. Science, University of Texasat Austin, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Comp. and Info. Science, University of Texasat Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033903615"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.5767,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81662592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2011","issue":null,"first_page":"562","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9801999926567078,"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/software-portability","display_name":"Software portability","score":0.8801995515823364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8743137717247009},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8634046316146851},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.6734081506729126},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6200492978096008},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5634204149246216},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.481354296207428},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.46087437868118286},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.428458034992218},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4272368550300598},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.426516592502594},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4262898862361908},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41316288709640503},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38825714588165283},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3255019187927246},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26143479347229004},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2178409993648529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17357856035232544}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8801995515823364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8743137717247009},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8634046316146851},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6734081506729126},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6200492978096008},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5634204149246216},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.481354296207428},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.46087437868118286},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.428458034992218},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4272368550300598},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.426516592502594},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4262898862361908},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41316288709640503},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38825714588165283},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3255019187927246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26143479347229004},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2178409993648529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17357856035232544},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/hpcsim.2016.7568385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2016.7568385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W110609005","https://openalex.org/W1039217118","https://openalex.org/W1537323515","https://openalex.org/W1790519466","https://openalex.org/W1965055558","https://openalex.org/W1975001341","https://openalex.org/W2033088400","https://openalex.org/W2036668966","https://openalex.org/W2055312318","https://openalex.org/W2062368747","https://openalex.org/W2067479799","https://openalex.org/W2075745057","https://openalex.org/W2079961815","https://openalex.org/W2081245617","https://openalex.org/W2084917734","https://openalex.org/W2102182691","https://openalex.org/W2104512032","https://openalex.org/W2107911628","https://openalex.org/W2119395117","https://openalex.org/W2143609451","https://openalex.org/W2153637321","https://openalex.org/W2155028447","https://openalex.org/W2166247098","https://openalex.org/W2548523184","https://openalex.org/W3103983137","https://openalex.org/W3105204543","https://openalex.org/W4230183876","https://openalex.org/W4251637954","https://openalex.org/W4255653201","https://openalex.org/W6627074740","https://openalex.org/W6729030020"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W1872724644","https://openalex.org/W3094539685","https://openalex.org/W4239524870","https://openalex.org/W2955328870","https://openalex.org/W2166713816","https://openalex.org/W4221075948","https://openalex.org/W4214517608"],"abstract_inverted_index":{"Modern":[0],"computer":[1],"systems":[2,19],"typically":[3],"conbine":[4],"multicore":[5],"CPUs":[6],"with":[7,46,59,119],"accelerators":[8],"like":[9],"GPUs":[10],"for":[11,28,154],"inproved":[12],"performance":[13,23,37,82,95,164],"and":[14,51,70,105,178,181],"energy":[15],"efficiency.":[16],"However,":[17],"these":[18],"suffer":[20],"from":[21,49,157],"poor":[22],"portability":[24],"-":[25],"code":[26],"tuned":[27],"one":[29],"device":[30],"must":[31],"be":[32],"retuned":[33],"to":[34,53,88,101,135,139,184,199],"achieve":[35],"high":[36,151],"on":[38,56,90,125,170,175],"another.":[39],"Image":[40],"processing":[41,173],"is":[42,99],"increasing":[43],"in":[44,192],"importance,":[45],"applications":[47],"ranging":[48],"seismology":[50],"medicine":[52],"Photoshop.":[54],"Based":[55],"our":[57,102,111,142,168],"experience":[58],"medical":[60],"image":[61,172],"processing,":[62],"we":[63,148],"propose":[64],"ImageCL,":[65],"a":[66,158],"high-level":[67,108],"domain-specific":[68],"language":[69],"source-to-source":[71,103,112],"compiler,":[72],"targeting":[73],"heterogeneous":[74],"hardware.":[75],"ImageCL":[76,109],"resembles":[77],"OpenCL,":[78],"but":[79],"abstracts":[80],"away":[81],"optimization":[83],"details,":[84],"allowing":[85],"the":[86,189],"programmer":[87,133],"focus":[89],"algorithm":[91],"development,":[92],"rather":[93,127],"than":[94,128],"tuning.":[96],"The":[97],"latter":[98],"left":[100],"compiler":[104,113],"auto-tuner.":[106],"From":[107],"kernels,":[110],"can":[114,149],"generate":[115,150],"multiple":[116],"OpenCL":[117],"implementations":[118,153],"different":[120,155,176],"optimizations":[121,138],"applied.":[122],"We":[123,166],"rely":[124],"auto-tuning":[126],"machine":[129],"models":[130],"or":[131],"expert":[132],"knowledge":[134],"determine":[136],"which":[137],"apply,":[140],"making":[141],"tuning":[143],"procedure":[144],"highly":[145],"robust.":[146],"Furthermore,":[147],"performing":[152],"devices":[156],"single":[159],"source":[160],"code,":[161],"thereby":[162],"improving":[163],"portability.":[165],"evaluate":[167],"approach":[169],"three":[171],"benchmarks,":[174],"GPU":[177],"CPU":[179],"devices,":[180],"are":[182],"able":[183],"outperform":[185],"other":[186],"state":[187],"of":[188,197],"art":[190],"solutions":[191],"several":[193],"cases,":[194],"achieving":[195],"speedups":[196],"up":[198],"4.57x.":[200]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}