{"id":"https://openalex.org/W4414197189","doi":"https://doi.org/10.1109/dac63849.2025.11133141","title":"DataMaestro: A Versatile and Efficient Data Streaming Engine Bringing Decoupled Memory Access To Dataflow Accelerators","display_name":"DataMaestro: A Versatile and Efficient Data Streaming Engine Bringing Decoupled Memory Access To Dataflow Accelerators","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4414197189","doi":"https://doi.org/10.1109/dac63849.2025.11133141"},"language":"en","primary_location":{"id":"doi:10.1109/dac63849.2025.11133141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (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/A5044800775","display_name":"Xun Yi","orcid":"https://orcid.org/0009-0003-3001-3611"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Xiaoling Yi","raw_affiliation_strings":["KU Leuven,MICAS-ESAT,Leuven,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS-ESAT,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047843365","display_name":"Yimin Deng","orcid":"https://orcid.org/0000-0002-3940-2918"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Yunhao Deng","raw_affiliation_strings":["KU Leuven,MICAS-ESAT,Leuven,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS-ESAT,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058316243","display_name":"Ryan Antonio","orcid":"https://orcid.org/0000-0002-0286-4609"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Ryan Antonio","raw_affiliation_strings":["KU Leuven,MICAS-ESAT,Leuven,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS-ESAT,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030661973","display_name":"Fei Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Fanchen Kong","raw_affiliation_strings":["KU Leuven,MICAS-ESAT,Leuven,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS-ESAT,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064318827","display_name":"Guilherme Paim","orcid":"https://orcid.org/0000-0001-7809-9563"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Guilherme Paim","raw_affiliation_strings":["Universidade de Lisboa,INESC-ID, Instituto Superior T&#x00E9;cnico,Lisboa,Portugal"],"affiliations":[{"raw_affiliation_string":"Universidade de Lisboa,INESC-ID, Instituto Superior T&#x00E9;cnico,Lisboa,Portugal","institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012150553","display_name":"Marian Verhelst","orcid":"https://orcid.org/0000-0003-3495-9263"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marian Verhelst","raw_affiliation_strings":["KU Leuven,MICAS-ESAT,Leuven,Belgium"],"affiliations":[{"raw_affiliation_string":"KU Leuven,MICAS-ESAT,Leuven,Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044800775"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":4.3965,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94533995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9914000034332275,"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":0.9914000034332275,"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":0.9855999946594238,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9854000210762024,"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/dataflow","display_name":"Dataflow","score":0.8151999711990356},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.6419000029563904},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4918000102043152},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4844000041484833},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.45260000228881836},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.43790000677108765},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4235999882221222},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41940000653266907},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482000231742859},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8151999711990356},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.6419000029563904},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.507099986076355},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4918000102043152},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.35830000042915344},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac63849.2025.11133141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac63849.2025.11133141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 62nd ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964471912","https://openalex.org/W1983394510","https://openalex.org/W2154790323","https://openalex.org/W2302255633","https://openalex.org/W2604319603","https://openalex.org/W2626953429","https://openalex.org/W2925491732","https://openalex.org/W2940862705","https://openalex.org/W3007788310","https://openalex.org/W3013692244","https://openalex.org/W3016309475","https://openalex.org/W3091969046","https://openalex.org/W3094406919","https://openalex.org/W3132942233","https://openalex.org/W3157657667","https://openalex.org/W3191906639","https://openalex.org/W3205706264","https://openalex.org/W3211076556","https://openalex.org/W3213528054","https://openalex.org/W4239659666","https://openalex.org/W4244024631","https://openalex.org/W4251000960","https://openalex.org/W4313467202","https://openalex.org/W4360605374","https://openalex.org/W4377969807","https://openalex.org/W4383215281","https://openalex.org/W4393406875","https://openalex.org/W4400726528","https://openalex.org/W4401211619","https://openalex.org/W4401212157","https://openalex.org/W4401880104"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"across":[8],"various":[9],"intelligent":[10],"tasks":[11],"but":[12],"encounter":[13],"performance":[14],"and":[15,31,53,62,67,75,85,98,112,139,145],"energy":[16,140],"challenges":[17],"in":[18],"inference":[19],"execution":[20],"due":[21],"to":[22,42,46,57,71,81,142],"data":[23,33,79],"movement":[24],"bottlenecks.":[25],"We":[26,88],"introduce":[27],"DataMaestro,":[28],"a":[29,93,99,103],"versatile":[30],"efficient":[32],"streaming":[34],"unit":[35],"that":[36,117],"brings":[37],"the":[38,120,148],"decoupled":[39],"access/execute":[40],"architecture":[41],"DNN":[43],"dataflow":[44],"accelerators":[45],"address":[47],"this":[48],"issue.":[49],"DataMaestro":[50,118],"supports":[51],"flexible":[52],"programmable":[54],"access":[55,86],"patterns":[56],"accommodate":[58],"diverse":[59],"workload":[60],"types":[61],"dataflows,":[63],"incorporates":[64],"fine-grained":[65],"prefetch":[66],"addressing":[68],"mode":[69],"switching":[70],"mitigate":[72],"bank":[73],"conflicts,":[74],"enables":[76],"customizable":[77],"on-the-fly":[78],"manipulation":[80],"reduce":[82],"memory":[83],"footprints":[84],"counts.":[87],"integrate":[89],"five":[90],"DataMaestros":[91],"with":[92],"Tensor":[94],"Core-like":[95],"GeMM":[96,121],"accelerator":[97,101],"Quantization":[100],"into":[102],"RISC-V":[104],"host":[105],"system":[106],"for":[107],"evaluation.":[108],"The":[109],"FPGA":[110],"prototype":[111],"VLSI":[113],"synthesis":[114],"results":[115],"demonstrate":[116],"helps":[119],"core":[122],"achieve":[123],"nearly":[124],"100%":[125],"utilization,":[126],"which":[127],"is":[128],"1.05":[129],"$21.39":[130],"\\times$":[131],"better":[132],"than":[133],"state-of-the-art":[134],"solutions,":[135],"while":[136],"minimizing":[137],"area":[138],"consumption":[141],"merely":[143],"6.43%":[144],"15.06%":[146],"of":[147],"total":[149],"system.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
