{"id":"https://openalex.org/W4386568643","doi":"https://doi.org/10.1145/3609109","title":"Let Coarse-Grained Resources Be Shared: Mapping Entire Neural Networks on FPGAs","display_name":"Let Coarse-Grained Resources Be Shared: Mapping Entire Neural Networks on FPGAs","publication_year":2023,"publication_date":"2023-09-09","ids":{"openalex":"https://openalex.org/W4386568643","doi":"https://doi.org/10.1145/3609109"},"language":"en","primary_location":{"id":"doi:10.1145/3609109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609109","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-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/A5003112703","display_name":"Tzung-Han Juang","orcid":"https://orcid.org/0000-0003-1629-8617"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Tzung-Han Juang","raw_affiliation_strings":["McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047154846","display_name":"Christof Schlaak","orcid":"https://orcid.org/0000-0002-3835-4774"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christof Schlaak","raw_affiliation_strings":["University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229154","display_name":"Christophe Dubach","orcid":"https://orcid.org/0000-0003-4811-2469"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Christophe Dubach","raw_affiliation_strings":["McGill University &amp; Mila, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University &amp; Mila, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003112703"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.9227,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71843593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"22","issue":"5s","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8739656209945679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8680940270423889},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7642600536346436},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.559540867805481},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.541276216506958},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5159524083137512},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5159100294113159},{"id":"https://openalex.org/keywords/shared-resource","display_name":"Shared resource","score":0.5087657570838928},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.42323172092437744},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.4201483428478241},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37993744015693665},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3585057258605957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1569223701953888},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1133822500705719},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10152938961982727}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8739656209945679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8680940270423889},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7642600536346436},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.559540867805481},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.541276216506958},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5159524083137512},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5159100294113159},{"id":"https://openalex.org/C51332947","wikidata":"https://www.wikidata.org/wiki/Q1172305","display_name":"Shared resource","level":2,"score":0.5087657570838928},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.42323172092437744},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.4201483428478241},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37993744015693665},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3585057258605957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1569223701953888},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1133822500705719},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10152938961982727},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3609109","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3609109","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1983394510","https://openalex.org/W2018055497","https://openalex.org/W2075745057","https://openalex.org/W2098394034","https://openalex.org/W2138209363","https://openalex.org/W2263852834","https://openalex.org/W2513568085","https://openalex.org/W2613159291","https://openalex.org/W2626616508","https://openalex.org/W2757637133","https://openalex.org/W2798482398","https://openalex.org/W2798804265","https://openalex.org/W2896983500","https://openalex.org/W2906737788","https://openalex.org/W2954600699","https://openalex.org/W3006236305","https://openalex.org/W3007901542","https://openalex.org/W3015861875","https://openalex.org/W3023624105","https://openalex.org/W3033414614","https://openalex.org/W3033664232","https://openalex.org/W3148529197","https://openalex.org/W3215210342","https://openalex.org/W4210570899","https://openalex.org/W4233429846","https://openalex.org/W4253267708","https://openalex.org/W4281750399","https://openalex.org/W4293025825"],"related_works":["https://openalex.org/W2612099726","https://openalex.org/W2531450434","https://openalex.org/W2014165129","https://openalex.org/W2367348190","https://openalex.org/W594316872","https://openalex.org/W2831860248","https://openalex.org/W2367794224","https://openalex.org/W2072850836","https://openalex.org/W2017163657","https://openalex.org/W1968650434"],"abstract_inverted_index":{"Traditional":[0],"High-Level":[1],"Synthesis":[2],"(HLS)":[3],"provides":[4],"rapid":[5],"prototyping":[6],"of":[7],"hardware":[8],"accelerators":[9],"without":[10],"coding":[11],"with":[12],"Hardware":[13],"Description":[14],"Languages":[15],"(HDLs).":[16],"However,":[17],"such":[18],"an":[19],"approach":[20,43],"does":[21],"not":[22,52],"well":[23],"support":[24],"allocating":[25],"large":[26],"applications":[27],"like":[28],"entire":[29,101],"deep":[30],"neural":[31,102],"networks":[32,103],"on":[33,72,104],"a":[34],"single":[35],"Field":[36],"Programmable":[37],"Gate":[38],"Array":[39],"(FPGA)":[40],"device.":[41],"The":[42,80],"leads":[44],"to":[45,57,63,112],"designs":[46,66],"that":[47],"are":[48],"inefficient":[49],"or":[50],"do":[51],"fit":[53],"into":[54],"FPGAs":[55,105],"due":[56],"resource":[58,69],"constraints.":[59],"This":[60],"work":[61],"proposes":[62],"shrink":[64],"generated":[65],"by":[67],"coarse-grained":[68],"control":[70],"based":[71],"function":[73],"sharing":[74],"in":[75],"functional":[76],"Intermediate":[77],"Representations":[78],"(IRs).":[79],"proposed":[81],"compiler":[82],"passes":[83],"and":[84,93,107],"rewrite":[85],"system":[86],"aim":[87],"at":[88],"producing":[89],"valid":[90],"design":[91],"points":[92],"removing":[94],"redundant":[95],"hardware.":[96],"Such":[97],"optimizations":[98],"make":[99],"fitting":[100],"feasible":[106],"produce":[108],"competitive":[109],"performance":[110],"compared":[111],"running":[113],"specialized":[114],"kernels":[115],"for":[116],"each":[117],"layer.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
