{"id":"https://openalex.org/W2104659803","doi":"https://doi.org/10.1109/ipdps.2010.5470423","title":"Optimal loop unrolling for GPGPU programs","display_name":"Optimal loop unrolling for GPGPU programs","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2104659803","doi":"https://doi.org/10.1109/ipdps.2010.5470423","mag":"2104659803"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://etd.ohiolink.edu/acprod/odb_etd/ws/send_file/send?accession=osu1253131903&disposition=inline","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052967446","display_name":"Giridhar Sreenivasa Murthy","orcid":"https://orcid.org/0009-0006-4208-8137"},"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":"Giridhar Sreenivasa Murthy","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023732985","display_name":"M. Ravishankar","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":false,"raw_author_name":"Mahesh Ravishankar","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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":false,"raw_author_name":"Muthu Manikandan Baskaran","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio 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":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering; The Ohio State University; Columbus Ohio USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052967446"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":4.8011,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.95405079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"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":0.9968000054359436,"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":0.9966999888420105,"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/loop-unrolling","display_name":"Loop unrolling","score":0.9092273712158203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8840024471282959},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.8068221807479858},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.8049020767211914},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8012778759002686},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7363909482955933},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.5357422232627869},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.45117655396461487},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.435413122177124},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4194835424423218},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20940178632736206},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07697436213493347}],"concepts":[{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.9092273712158203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8840024471282959},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.8068221807479858},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8049020767211914},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8012778759002686},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7363909482955933},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5357422232627869},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.45117655396461487},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.435413122177124},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4194835424423218},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20940178632736206},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07697436213493347}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2010.5470423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:etd.ohiolink.edu:osu1253131903","is_oa":true,"landing_page_url":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1253131903","pdf_url":"https://etd.ohiolink.edu/acprod/odb_etd/ws/send_file/send?accession=osu1253131903&disposition=inline","source":{"id":"https://openalex.org/S4377196344","display_name":"OhioLink ETD Center (Ohio Library and Information Network)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210155183","host_organization_name":"Ohio Library and Information Network","host_organization_lineage":["https://openalex.org/I4210155183"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1253131903","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:etd.ohiolink.edu:osu1253131903","is_oa":true,"landing_page_url":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1253131903","pdf_url":"https://etd.ohiolink.edu/acprod/odb_etd/ws/send_file/send?accession=osu1253131903&disposition=inline","source":{"id":"https://openalex.org/S4377196344","display_name":"OhioLink ETD Center (Ohio Library and Information Network)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210155183","host_organization_name":"Ohio Library and Information Network","host_organization_lineage":["https://openalex.org/I4210155183"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rave.ohiolink.edu/etdc/view?acc_num=osu1253131903","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2104659803.pdf","grobid_xml":"https://content.openalex.org/works/W2104659803.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1568272005","https://openalex.org/W1982825626","https://openalex.org/W1984205637","https://openalex.org/W2020634604","https://openalex.org/W2026048928","https://openalex.org/W2028499920","https://openalex.org/W2083056254","https://openalex.org/W2095292158","https://openalex.org/W2098891450","https://openalex.org/W2121546953","https://openalex.org/W2138007781","https://openalex.org/W2141084005","https://openalex.org/W2141962648","https://openalex.org/W2153492376","https://openalex.org/W2154370333","https://openalex.org/W2158161220","https://openalex.org/W2160786443","https://openalex.org/W2171072418","https://openalex.org/W2231791608","https://openalex.org/W4256526202","https://openalex.org/W6683787511","https://openalex.org/W6689165056"],"related_works":["https://openalex.org/W3169195854","https://openalex.org/W1498734356","https://openalex.org/W2010414531","https://openalex.org/W2133860611","https://openalex.org/W2889110163","https://openalex.org/W2104659803","https://openalex.org/W2171072418","https://openalex.org/W2901114907","https://openalex.org/W1542326246","https://openalex.org/W2553479971"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"are":[4],"massively":[5],"parallel,":[6],"many-core":[7],"processors":[8],"with":[9,55],"tremendous":[10],"computational":[11],"power":[12],"and":[13,30,49,60,133,156],"very":[14,43],"high":[15],"memory":[16],"bandwidth.":[17],"With":[18],"the":[19,31,46,86,118,126,129,134,145,162,176],"advent":[20],"of":[21,88,120,128,147,153],"general":[22,35],"purpose":[23,36],"programming":[24,37,50],"models":[25],"such":[26,66],"as":[27],"NVIDIA's":[28],"CUDA":[29],"new":[32,58],"standard":[33],"OpenCL,":[34],"using":[38],"GPUs":[39],"(GPGPU)":[40],"has":[41],"become":[42],"popular.":[44],"However,":[45],"GPU":[47,73],"architecture":[48],"model":[51],"have":[52],"brought":[53],"along":[54],"it":[56],"many":[57],"challenges":[59],"opportunities":[61],"for":[62,100,105,116],"compiler":[63],"optimizations.":[64],"One":[65],"classical":[67],"optimization":[68],"is":[69],"loop":[70,77,89,148],"unrolling.":[71,78],"Current":[72],"compilers":[74],"perform":[75],"limited":[76],"In":[79,111],"this":[80],"paper,":[81],"we":[82,113,159],"attempt":[83],"to":[84,143,171],"understand":[85],"impact":[87],"unrolling":[90,149],"on":[91,125,150],"GPGPU":[92,109,154],"programs.":[93,110],"We":[94,139],"develop":[95],"a":[96,151],"semi-automatic,":[97],"compile-time":[98],"approach":[99],"identifying":[101],"optimal":[102,163],"unroll":[103,121,164],"factors":[104,122],"suitable":[106],"loops":[107],"in":[108],"addition,":[112],"propose":[114],"techniques":[115,142],"reducing":[117],"number":[119],"evaluated,":[123],"based":[124],"characteristics":[127],"program":[130],"being":[131,136],"compiled":[132,137],"device":[135],"to.":[138],"use":[140],"these":[141],"evaluate":[144],"effect":[146],"range":[152],"programs":[155],"show":[157],"that":[158],"correctly":[160],"identify":[161],"factors.":[165],"The":[166],"optimized":[167],"versions":[168],"run":[169],"up":[170],"70":[172],"percent":[173],"faster":[174],"than":[175],"unoptimized":[177],"versions.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}