{"id":"https://openalex.org/W3214146924","doi":"https://doi.org/10.1145/3546070","title":"Early DSE and Automatic Generation of Coarse-grained Merged Accelerators","display_name":"Early DSE and Automatic Generation of Coarse-grained Merged Accelerators","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W3214146924","doi":"https://doi.org/10.1145/3546070","mag":"3214146924"},"language":"en","primary_location":{"id":"doi:10.1145/3546070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546070","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/A5014379085","display_name":"Iulian Brumar","orcid":"https://orcid.org/0000-0003-0403-856X"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iulian Brumar","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0403-856X","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087962654","display_name":"Georgios Zacharopoulos","orcid":"https://orcid.org/0000-0002-6644-5200"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgios Zacharopoulos","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6644-5200","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101953376","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0001-7479-9263"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Yao","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7479-9263","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053283610","display_name":"Saketh Rama","orcid":"https://orcid.org/0000-0001-9528-5966"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saketh Rama","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9528-5966","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026496503","display_name":"David Brooks","orcid":"https://orcid.org/0000-0002-0662-7889"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Brooks","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0662-7889","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043327132","display_name":"Gu-Yeon Wei","orcid":"https://orcid.org/0000-0001-5730-9904"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu-Yeon Wei","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5730-9904","affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014379085"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":1.8676,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83473892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"22","issue":"2","first_page":"1","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization 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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9065605401992798},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.7070549726486206},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5693708062171936},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.503391444683075},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5006017684936523},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.49826717376708984},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46390101313591003},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.43267685174942017},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4324626922607422},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.41426002979278564},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3850218951702118},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37291815876960754},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3497686982154846},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18108180165290833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9065605401992798},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.7070549726486206},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5693708062171936},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.503391444683075},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5006017684936523},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.49826717376708984},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46390101313591003},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.43267685174942017},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4324626922607422},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.41426002979278564},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3850218951702118},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37291815876960754},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3497686982154846},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18108180165290833},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3546070","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3546070","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1970032753","https://openalex.org/W1982205631","https://openalex.org/W2000967104","https://openalex.org/W2012114780","https://openalex.org/W2036853599","https://openalex.org/W2042928023","https://openalex.org/W2074231493","https://openalex.org/W2098133383","https://openalex.org/W2109607425","https://openalex.org/W2127637733","https://openalex.org/W2145601734","https://openalex.org/W2150843905","https://openalex.org/W2152839228","https://openalex.org/W2153185479","https://openalex.org/W2162385899","https://openalex.org/W2294320930","https://openalex.org/W2410641680","https://openalex.org/W2517041198","https://openalex.org/W2561995440","https://openalex.org/W2618564128","https://openalex.org/W2625058759","https://openalex.org/W2786332448","https://openalex.org/W2789928742","https://openalex.org/W2798482398","https://openalex.org/W2890660991","https://openalex.org/W2906737788","https://openalex.org/W2921888067","https://openalex.org/W3006559397","https://openalex.org/W3033154127","https://openalex.org/W3033664232","https://openalex.org/W3090389586","https://openalex.org/W3090891670","https://openalex.org/W3106090013","https://openalex.org/W4225564528","https://openalex.org/W4230315356","https://openalex.org/W4234863022","https://openalex.org/W4241251112","https://openalex.org/W4246166885","https://openalex.org/W4292169167","https://openalex.org/W4300461182"],"related_works":["https://openalex.org/W4281926497","https://openalex.org/W2269990635","https://openalex.org/W2108242004","https://openalex.org/W2042762783","https://openalex.org/W4283730710","https://openalex.org/W4281784598","https://openalex.org/W2129913821","https://openalex.org/W4313484792","https://openalex.org/W4282568311","https://openalex.org/W4295935044"],"abstract_inverted_index":{"Post-Moore\u2019s":[0],"law":[1],"area-constrained":[2],"systems":[3],"rely":[4],"on":[5,192],"accelerators":[6,12,46,110,128,155],"to":[7,25,71,84,94,105,111,117,152,170,185,196],"deliver":[8],"performance":[9,181],"enhancements.":[10],"Coarse-grained":[11],"can":[13,129],"offer":[14],"substantial":[15],"domain":[16],"acceleration,":[17],"but":[18],"manual,":[19],"ad":[20],"hoc":[21],"identification":[22],"of":[23,44,135,138,183],"code":[24],"accelerate":[26],"is":[27,57,143],"prohibitively":[28],"expensive.":[29],"Because":[30],"cycle-accurate":[31],"simulators":[32],"and":[33,50,75,89,91,107,116,124,190],"high-level":[34],"synthesis":[35],"(HLS)":[36],"flows":[37,165],"are":[38],"so":[39],"time-consuming,":[40],"the":[41,67,136,172],"manual":[42,168],"creation":[43],"high-utilization":[45],"that":[47],"exploit":[48],"control":[49],"data":[51],"flow":[52],"patterns":[53],"at":[54],"optimal":[55,148],"granularities":[56],"rarely":[58],"successful.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64],"present":[65],"AccelMerger,":[66],"first":[68],"automated":[69],"methodology":[70],"create":[72],"coarse-grained,":[73],"control-":[74],"data-flow-rich":[76],"merged":[77],"accelerators.":[78],"AccelMerger":[79,178],"uses":[80],"sequence":[81],"alignment":[82],"matching":[83],"recognize":[85],"similar":[86],"function":[87],"call-graphs":[88],"loops,":[90],"neural":[92],"networks":[93],"quickly":[95],"evaluate":[96],"their":[97],"post-HLS":[98],"characteristics.":[99],"It":[100],"accurately":[101],"identifies":[102],"which":[103],"functions":[104],"accelerate,":[106],"it":[108],"merges":[109],"respect":[112,195],"an":[113],"area":[114,137],"budget":[115],"accommodate":[118],"system":[119],"communication":[120],"characteristics":[121],"like":[122],"latency":[123],"bandwidth.":[125],"Merging":[126],"two":[127],"save":[130],"as":[131,133],"much":[132],"99%":[134],"one.":[139],"The":[140],"space":[141,200],"saved":[142],"used":[144],"by":[145],"a":[146],"globally":[147],"integer":[149],"linear":[150],"program":[151],"allocate":[153],"more":[154],"for":[156],"increased":[157],"performance.":[158],"We":[159],"demonstrate":[160],"AccelMerger\u2019s":[161],"effectiveness":[162],"using":[163],"HLS":[164],"without":[166],"any":[167],"effort":[169],"fine-tune":[171],"resulting":[173],"designs.":[174],"On":[175],"FPGA-based":[176],"systems,":[177],"yields":[179],"application":[180],"improvements":[182],"up":[184],"16.7\u00d7":[186],"over":[187],"software":[188],"implementations,":[189],"1.91\u00d7":[191],"average":[193],"with":[194],"state-of-the-art":[197],"early-stage":[198],"design":[199],"exploration":[201],"tools.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
