{"id":"https://openalex.org/W2083056254","doi":"https://doi.org/10.1145/1375527.1375562","title":"A compiler framework for optimization of affine loop nests for gpgpus","display_name":"A compiler framework for optimization of affine loop nests for gpgpus","publication_year":2008,"publication_date":"2008-06-07","ids":{"openalex":"https://openalex.org/W2083056254","doi":"https://doi.org/10.1145/1375527.1375562","mag":"2083056254"},"language":"en","primary_location":{"id":"doi:10.1145/1375527.1375562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","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/A5104040289","display_name":"Muthu Manikandan Baskaran","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Muthu Manikandan Baskaran","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025342111","display_name":"Uday Bondhugula","orcid":"https://orcid.org/0000-0002-8297-6159"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uday Bondhugula","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057117526","display_name":"J. Ramanujam","orcid":"https://orcid.org/0000-0002-4349-1327"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Ramanujam","raw_affiliation_strings":["Louisiana State University, Baton Rouge, LA, USA"],"affiliations":[{"raw_affiliation_string":"Louisiana State University, Baton Rouge, LA, USA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039624297","display_name":"Atanas Rountev","orcid":"https://orcid.org/0000-0003-4556-4937"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","The Ohio State University, Columbus, OH, USA.;"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA.;","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104040289"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":16.62588373,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99710317,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"234"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/loop-unrolling","display_name":"Loop unrolling","score":0.9180774688720703},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9025940895080566},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8223016262054443},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7754153609275818},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7660769820213318},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.6206079125404358},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.5963089466094971},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.5606294870376587},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5384016633033752},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49364838004112244},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.49094370007514954},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4888426661491394},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4046753942966461},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.13779276609420776}],"concepts":[{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.9180774688720703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9025940895080566},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8223016262054443},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7754153609275818},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7660769820213318},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.6206079125404358},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.5963089466094971},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5606294870376587},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5384016633033752},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49364838004112244},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.49094370007514954},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4888426661491394},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4046753942966461},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.13779276609420776},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1375527.1375562","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1375527.1375562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-2618","is_oa":false,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/1616","pdf_url":null,"source":{"id":"https://openalex.org/S4404675853","display_name":"Faculty publications","issn_l":"3008-1017","issn":["3008-1017"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1486289306","https://openalex.org/W1533186609","https://openalex.org/W1591453641","https://openalex.org/W1970141743","https://openalex.org/W1992851788","https://openalex.org/W1995270665","https://openalex.org/W2032309817","https://openalex.org/W2032391783","https://openalex.org/W2034761517","https://openalex.org/W2038543880","https://openalex.org/W2097699872","https://openalex.org/W2108792719","https://openalex.org/W2116963870","https://openalex.org/W2128249697","https://openalex.org/W2132331020","https://openalex.org/W2139143992","https://openalex.org/W2139774022","https://openalex.org/W2142655718","https://openalex.org/W2151406013","https://openalex.org/W2153492376","https://openalex.org/W2163229756","https://openalex.org/W2620746779","https://openalex.org/W3203568064","https://openalex.org/W4241513866","https://openalex.org/W6738527174"],"related_works":["https://openalex.org/W1498734356","https://openalex.org/W2010414531","https://openalex.org/W3169195854","https://openalex.org/W2122418911","https://openalex.org/W4251798485","https://openalex.org/W2889110163","https://openalex.org/W4232588022","https://openalex.org/W2133860611","https://openalex.org/W2166906890","https://openalex.org/W3081462789"],"abstract_inverted_index":{"GPUs":[0,40],"are":[1,52],"a":[2,48,59,88,129],"class":[3],"of":[4,25,35,50,57,68,92,101,131,136],"specialized":[5],"parallel":[6,37],"architectures":[7],"with":[8],"tremendous":[9],"computational":[10],"power.":[11],"The":[12],"new":[13],"Compute":[14],"Unified":[15],"Device":[16],"Architecture":[17],"(CUDA)":[18],"programming":[19,24],"model":[20,91],"from":[21,83,109],"NVIDIA":[22],"facilitates":[23],"general":[26],"purpose":[27],"applications":[28],"on":[29,72,128],"their":[30],"GPUs,":[31],"However,":[32],"manual":[33],"development":[34],"high-performance":[36],"code":[38],"for":[39,62,79,105,122],"is":[41],"still":[42],"very":[43],"challenging.":[44],"In":[45],"this":[46],"paper,":[47],"number":[49,130],"issues":[51],"addressed":[53],"towards":[54],"the":[55,134,137],"goal":[56],"developing":[58],"compiler":[60,90,138],"framework":[61],"automatic":[63],"parallelization":[64],"and":[65,96,113,124],"performance":[66],"optimization":[67,139],"affine":[69],"loop":[70],"nests":[71],"GPGPUs:":[73],"1)":[74],"approach":[75],"to":[76,118],"program":[77,97],"transformation":[78],"efficient":[80],"data":[81,93,107],"access":[82,108],"GPU":[84,110],"global":[85],"memory,":[86],"using":[87],"polyhedral":[89],"dependence":[94],"abstraction":[95],"transformation;":[98],"2)":[99],"determination":[100],"optimal":[102,120],"padding":[103],"factors":[104],"conflict-minimal":[106],"shared":[111],"memory;":[112],"3)":[114],"model-driven":[115],"empirical":[116],"search":[117],"determine":[119],"parameters":[121],"unrolling":[123],"tiling.":[125],"Experimental":[126],"results":[127],"kernels":[132],"demonstrate":[133],"effectiveness":[135],"approaches":[140],"developed.":[141],"Copyright":[142],"2008":[143],"ACM.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":26},{"year":2012,"cited_by_count":20}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}