{"id":"https://openalex.org/W2016563136","doi":"https://doi.org/10.1145/2207222.2207225","title":"A unified optimizing compiler framework for different GPGPU architectures","display_name":"A unified optimizing compiler framework for different GPGPU architectures","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2016563136","doi":"https://doi.org/10.1145/2207222.2207225","mag":"2016563136"},"language":"en","primary_location":{"id":"doi:10.1145/2207222.2207225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2207222.2207225","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2207222.2207225","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2207222.2207225","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101850483","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0963-6975"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053923667","display_name":"Ping Xiang","orcid":"https://orcid.org/0000-0002-1636-4111"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Xiang","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004127257","display_name":"Jingfei Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jingfei Kong","raw_affiliation_strings":["Advanced Micro Devices"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085469786","display_name":"Mike Mantor","orcid":null},"institutions":[{"id":"https://openalex.org/I1311921367","display_name":"Advanced Micro Devices (Canada)","ror":"https://ror.org/02yh0k313","country_code":"CA","type":"company","lineage":["https://openalex.org/I1311921367","https://openalex.org/I4210137977"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mike Mantor","raw_affiliation_strings":["Advanced Micro Devices"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices","institution_ids":["https://openalex.org/I1311921367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3174,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.87924493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9983999729156494,"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":0.9970999956130981,"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":0.8957831859588623},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8478059768676758},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8078309893608093},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7454434633255005},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.655920147895813},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.6130073666572571},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5893909931182861},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5621335506439209},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4647483229637146},{"id":"https://openalex.org/keywords/interprocedural-optimization","display_name":"Interprocedural optimization","score":0.438248872756958},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.3708188533782959},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23927679657936096},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14919763803482056},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.12983781099319458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8957831859588623},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8478059768676758},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8078309893608093},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7454434633255005},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.655920147895813},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.6130073666572571},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5893909931182861},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5621335506439209},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4647483229637146},{"id":"https://openalex.org/C111564260","wikidata":"https://www.wikidata.org/wiki/Q4288856","display_name":"Interprocedural optimization","level":5,"score":0.438248872756958},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.3708188533782959},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23927679657936096},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14919763803482056},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.12983781099319458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2207222.2207225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2207222.2207225","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2207222.2207225","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/2207222.2207225","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2207222.2207225","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2207222.2207225","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3999079424","display_name":null,"funder_award_id":"CCF-0968667","funder_id":"https://openalex.org/F4320337387","funder_display_name":"Division of Computing and Communication Foundations"}],"funders":[{"id":"https://openalex.org/F4320337387","display_name":"Division of Computing and Communication Foundations","ror":"https://ror.org/01mng8331"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2016563136.pdf","grobid_xml":"https://content.openalex.org/works/W2016563136.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1502558230","https://openalex.org/W1517684295","https://openalex.org/W1537323515","https://openalex.org/W1992851788","https://openalex.org/W2061171222","https://openalex.org/W2063186542","https://openalex.org/W2083056254","https://openalex.org/W2108600626","https://openalex.org/W2113282196","https://openalex.org/W2129232868","https://openalex.org/W2139143992","https://openalex.org/W2153492376","https://openalex.org/W2160786443","https://openalex.org/W2167334577","https://openalex.org/W2168519934","https://openalex.org/W2170634604"],"related_works":["https://openalex.org/W2121223013","https://openalex.org/W4246454774","https://openalex.org/W2083681681","https://openalex.org/W1488300410","https://openalex.org/W2091689272","https://openalex.org/W1597127505","https://openalex.org/W2099845707","https://openalex.org/W2053033210","https://openalex.org/W2036668966","https://openalex.org/W2016563136"],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,44],"novel":[4],"optimizing":[5],"compiler":[6,42,61],"for":[7,57,67,73,82],"general":[8],"purpose":[9],"computation":[10],"on":[11],"graphics":[12],"processing":[13],"units":[14],"(GPGPU).":[15],"It":[16],"addresses":[17],"two":[18,63],"major":[19],"challenges":[20],"of":[21,29,36],"developing":[22],"high":[23,97],"performance":[24,58],"GPGPU":[25],"programs:":[26],"effective":[27,81],"utilization":[28],"GPU":[30,46],"memory":[31],"hierarchy":[32],"and":[33,70,85],"judicious":[34],"management":[35],"parallelism.":[37],"The":[38,60,76,88],"input":[39],"to":[40,104],"our":[41,92],"is":[43,50,80],"na\u00efve":[45],"kernel":[47],"function,":[48],"which":[49],"functionally":[51],"correct":[52],"but":[53],"without":[54],"any":[55],"consideration":[56],"optimization.":[59],"generates":[62],"kernels,":[64],"one":[65],"optimized":[66,93],"global":[68],"memories":[69],"the":[71],"other":[72],"texture":[74],"memories.":[75],"proposed":[77],"compilation":[78],"process":[79],"both":[83],"AMD/ATI":[84],"NVIDIA":[86],"GPUs.":[87],"experiments":[89],"show":[90],"that":[91],"code":[94],"achieves":[95],"very":[96,102],"performance,":[98],"either":[99],"superior":[100],"or":[101],"close":[103],"highly":[105],"fine-tuned":[106],"libraries.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}