{"id":"https://openalex.org/W2293636967","doi":"https://doi.org/10.1109/aspdac.2016.7428062","title":"A scalable communication-aware compilation flow for programmable accelerators","display_name":"A scalable communication-aware compilation flow for programmable accelerators","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2293636967","doi":"https://doi.org/10.1109/aspdac.2016.7428062","mag":"2293636967"},"language":"en","primary_location":{"id":"doi:10.1109/aspdac.2016.7428062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2016.7428062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)","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/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101501969","display_name":"Hui Huang","orcid":"https://orcid.org/0000-0003-4474-7037"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084891530","display_name":"Mohammad Ali Ghodrat","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Ali Ghodrat","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016776689"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.2073,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86439722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"510"},"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":0.9995999932289124,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8746806383132935},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7854273319244385},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7451497912406921},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5844659805297852},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5239251255989075},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.5171741843223572},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.49879980087280273},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4493570029735565},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4229079484939575},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35490500926971436},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24335575103759766},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2128118872642517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8746806383132935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7854273319244385},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7451497912406921},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5844659805297852},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5239251255989075},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.5171741843223572},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.49879980087280273},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4493570029735565},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4229079484939575},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35490500926971436},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24335575103759766},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2128118872642517},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspdac.2016.7428062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2016.7428062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1990800384","https://openalex.org/W2036779190","https://openalex.org/W2080592089","https://openalex.org/W2089162427","https://openalex.org/W2104345864","https://openalex.org/W2118312929","https://openalex.org/W2120635877","https://openalex.org/W2122553095","https://openalex.org/W2123368544","https://openalex.org/W2128317332","https://openalex.org/W2130408605","https://openalex.org/W2133721425","https://openalex.org/W2145601734","https://openalex.org/W2148911285","https://openalex.org/W2155509874","https://openalex.org/W2164264749","https://openalex.org/W2164826555","https://openalex.org/W3151170728","https://openalex.org/W4250370106","https://openalex.org/W4252466729","https://openalex.org/W6654362743"],"related_works":["https://openalex.org/W2371266106","https://openalex.org/W2117382851","https://openalex.org/W3006505070","https://openalex.org/W2382449560","https://openalex.org/W2767298477","https://openalex.org/W2110432562","https://openalex.org/W2117864619","https://openalex.org/W2025344","https://openalex.org/W2090337950","https://openalex.org/W2104121286"],"abstract_inverted_index":{"Programmable":[0],"accelerators":[1,80],"(PA)":[2],"are":[3,24],"receiving":[4],"increased":[5],"attention":[6],"in":[7,81,118],"domain-specific":[8],"architecture":[9],"designs":[10],"to":[11,33,51,122,152],"provide":[12],"more":[13],"general":[14],"support":[15],"for":[16,104,133],"customization.":[17],"In":[18,91],"a":[19,40,82,164],"PA-rich":[20,83,110,167],"system,":[21],"computational":[22],"kernels":[23,108],"compiled":[25],"into":[26,109],"predefined":[27],"PA":[28,54,98,154],"templates":[29],"and":[30,116,147],"dynamically":[31],"mapped":[32],"real":[34],"PAs":[35],"at":[36,70],"runtime.":[37],"This":[38],"imposes":[39],"demanding":[41],"challenge":[42],"on":[43,163,178],"the":[44,61,87,119,138,160,170],"compiler":[45],"side":[46],"-":[47],"that":[48,132],"is,":[49],"how":[50],"generate":[52],"high-quality":[53],"mapping":[55,105,145],"code.":[56],"Another":[57],"important":[58],"concern":[59],"is":[60,102,114,174],"communication":[62,149],"cost":[63,150],"among":[64,75,127],"PAs:":[65],"if":[66],"not":[67],"handled":[68],"properly":[69],"compile":[71],"time,":[72],"data":[73,125],"transfers":[74,126],"tens":[76],"or":[77],"hundreds":[78],"of":[79],"system":[84],"will":[85],"limit":[86],"overall":[88,148],"performance":[89,172],"gain.":[90],"this":[92],"paper":[93],"we":[94],"present":[95],"an":[96],"efficient":[97],"compilation":[99,143,155],"flow,":[100],"which":[101],"scalable":[103],"large":[106],"computation":[107],"architectures.":[111],"Communication":[112],"overhead":[113],"modeled":[115],"optimized":[117],"proposed":[120,139,161],"flow":[121,162],"reduce":[123],"runtime":[124],"accelerators.":[128],"Experimental":[129],"results":[130],"show":[131],"12":[134],"computation-intensive":[135],"standard":[136],"benchmarks,":[137],"approach":[140],"significantly":[141],"improves":[142],"scalability,":[144],"quality":[146],"compared":[151],"state-of-art":[153],"approaches.":[156],"We":[157],"also":[158],"evaluate":[159],"recently":[165],"developed":[166],"platform":[168],"[1];":[169],"final":[171],"gain":[173],"improved":[175],"by":[176],"49.5%":[177],"average.":[179]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}