{"id":"https://openalex.org/W2136262589","doi":"https://doi.org/10.1109/hpca.2009.4798266","title":"Bridging the computation gap between programmable processors and hardwired accelerators","display_name":"Bridging the computation gap between programmable processors and hardwired accelerators","publication_year":2009,"publication_date":"2009-02-01","ids":{"openalex":"https://openalex.org/W2136262589","doi":"https://doi.org/10.1109/hpca.2009.4798266","mag":"2136262589"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2009.4798266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2009.4798266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 15th International Symposium on High Performance Computer Architecture","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/A5058271220","display_name":"Kevin Fan","orcid":"https://orcid.org/0000-0003-4087-4856"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210138990","display_name":"Micro Magnetics (United States)","ror":"https://ror.org/046jf3z18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138990"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Fan","raw_affiliation_strings":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA","Parakinetics, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Parakinetics, Inc","institution_ids":["https://openalex.org/I4210138990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000650022","display_name":"Manjunath Kudlur","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manjunath Kudlur","raw_affiliation_strings":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","NVIDIA Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004292742","display_name":"Ganesh Dasika","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ganesh Dasika","raw_affiliation_strings":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.1149,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98164269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/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/T10829","display_name":"Interconnection Networks and Systems","score":0.9961000084877014,"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":0.8013120889663696},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6996635794639587},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5880117416381836},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5273369550704956},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.5211812853813171},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4847988188266754},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4742361903190613},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4741993546485901},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4608002007007599},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44254592061042786},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.4341311752796173},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4308396875858307},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4293665289878845},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2661857008934021},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17730337381362915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013120889663696},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6996635794639587},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5880117416381836},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5273369550704956},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.5211812853813171},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4847988188266754},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4742361903190613},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4741993546485901},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4608002007007599},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44254592061042786},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.4341311752796173},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4308396875858307},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4293665289878845},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2661857008934021},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17730337381362915},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpca.2009.4798266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2009.4798266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 15th International Symposium on High Performance Computer Architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.159.8165","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.159.8165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cccp.eecs.umich.edu/papers/fank-hpca09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1528202422","https://openalex.org/W1581708820","https://openalex.org/W2075137135","https://openalex.org/W2080859692","https://openalex.org/W2086663885","https://openalex.org/W2095211764","https://openalex.org/W2109876904","https://openalex.org/W2111981871","https://openalex.org/W2116304229","https://openalex.org/W2121406925","https://openalex.org/W2123412205","https://openalex.org/W2134886942","https://openalex.org/W2137570657","https://openalex.org/W2140169558","https://openalex.org/W2144133815","https://openalex.org/W2154209875","https://openalex.org/W2159324394","https://openalex.org/W2167672866","https://openalex.org/W2170669923","https://openalex.org/W4234479839","https://openalex.org/W4240165549","https://openalex.org/W4252370083","https://openalex.org/W6676851959","https://openalex.org/W6682520797","https://openalex.org/W6685144921"],"related_works":["https://openalex.org/W2005635288","https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2165367082","https://openalex.org/W2020341030","https://openalex.org/W4255097844","https://openalex.org/W2567660513"],"abstract_inverted_index":{"New":[0],"media":[1],"and":[2,35,68,115,119,158,179,198],"signal":[3],"processing":[4],"applications":[5],"demand":[6],"ever":[7],"higher":[8],"performance":[9],"while":[10,92,190],"operating":[11],"within":[12],"the":[13,59,83,105,117,144,150,160,202],"tight":[14],"power":[15,36,177,197],"constraints":[16],"of":[17,22,33,48,61,65,90,104,149],"mobile":[18],"devices.":[19],"A":[20,101,132],"range":[21],"hardware":[23,66],"implementations":[24],"is":[25,58,109,136,153,169],"available":[26,86],"to":[27,41,96,129,139,171,174,201],"deliver":[28],"computation":[29],"with":[30,155,159],"varying":[31],"degrees":[32],"area":[34,182,199],"efficiency,":[37],"from":[38],"general-purpose":[39],"processors":[40],"application-specific":[42],"integrated":[43],"circuits":[44],"(ASICs).":[45],"The":[46,147,166],"tradeoff":[47],"moving":[49],"towards":[50],"more":[51],"efficient":[52,127],"customized":[53,76,102],"solutions":[54],"such":[55],"as":[56,193,195],"ASICs":[57],"lack":[60],"flexibility":[62,95],"in":[63,125],"terms":[64],"reusability":[67],"programmability.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"a":[75,112,185],"semi-programmable":[77],"loop":[78,106,114],"accelerator":[79,107,152,168],"architecture":[80,108],"that":[81],"exploits":[82],"efficiency":[84,148,178,183,200],"gains":[85],"through":[87],"high":[88],"levels":[89],"customization,":[91],"maintaining":[93],"sufficient":[94],"execute":[97],"multiple":[98],"similar":[99],"loops.":[100],"instance":[103],"generated":[110],"for":[111],"particular":[113],"then":[116,137],"data":[118],"control":[120],"paths":[121],"are":[122],"proactively":[123],"generalized":[124],"an":[126],"manner":[128],"increase":[130],"flexibility.":[131],"compiler":[133],"mapping":[134],"phase":[135],"able":[138,170],"map":[140],"other":[141],"loops":[142],"onto":[143],"same":[145],"hardware.":[146],"programmable":[151,167],"compared":[154],"non-programmable":[156,203],"accelerators":[157],"OpenRISC":[161],"1200":[162],"general":[163,187],"purpose":[164,188],"processor.":[165],"achieve":[172],"up":[173],"34x":[175],"better":[176,181],"30x":[180],"than":[184],"simple":[186],"processor,":[189],"trading":[191],"off":[192],"little":[194],"2x":[196],"accelerator.":[204]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}