{"id":"https://openalex.org/W4388469806","doi":"https://doi.org/10.1109/tc.2023.3329930","title":"A High-Performance, Energy-Efficient Modular DMA Engine Architecture","display_name":"A High-Performance, Energy-Efficient Modular DMA Engine Architecture","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388469806","doi":"https://doi.org/10.1109/tc.2023.3329930"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2023.3329930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3329930","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","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/A5085591358","display_name":"Thomas Benz","orcid":"https://orcid.org/0000-0002-0326-9676"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Benz","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-0326-9676","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030416536","display_name":"Michael Rogenmoser","orcid":"https://orcid.org/0000-0003-4622-4862"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Rogenmoser","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4622-4862","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052998498","display_name":"Paul Scheffler","orcid":"https://orcid.org/0000-0003-4230-1381"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Paul Scheffler","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4230-1381","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025031387","display_name":"Samuel Riedel","orcid":"https://orcid.org/0000-0002-5772-6377"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Samuel Riedel","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-5772-6377","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017154351","display_name":"Alessandro Ottaviano","orcid":"https://orcid.org/0009-0000-9924-3536"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alessandro Ottaviano","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-9924-3536","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051253991","display_name":"Andreas Kurth","orcid":"https://orcid.org/0000-0001-5613-9544"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Kurth","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-5613-9544","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["Scalable Parallel Computing Laboratory (SPCL), ETH Zurich, Z&#x00FC;rich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-1333-9797","affiliations":[{"raw_affiliation_string":"Scalable Parallel Computing Laboratory (SPCL), ETH Zurich, Z&#x00FC;rich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043408422","display_name":"Luca Benini","orcid":"https://orcid.org/0000-0001-8068-3806"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["CH","IT"],"is_corresponding":false,"raw_author_name":"Luca Benini","raw_affiliation_strings":["Integrated Systems Laboratory (IIS), ETH Zurich, Switzerland","Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Bologna, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8068-3806","affiliations":[{"raw_affiliation_string":"Integrated Systems Laboratory (IIS), ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Electrical, Electronic and Information Engineering (DEI), University of Bologna, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1069,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93298476,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"73","issue":"1","first_page":"263","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9973000288009644,"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":0.8205858469009399},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6742159724235535},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6668693423271179},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5781318545341492},{"id":"https://openalex.org/keywords/forwarding-plane","display_name":"Forwarding plane","score":0.554516613483429},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.47235187888145447},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46117129921913147},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4377603530883789},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.42032235860824585},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20200425386428833},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18338176608085632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205858469009399},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6742159724235535},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6668693423271179},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5781318545341492},{"id":"https://openalex.org/C10597312","wikidata":"https://www.wikidata.org/wiki/Q5473302","display_name":"Forwarding plane","level":3,"score":0.554516613483429},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.47235187888145447},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46117129921913147},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4377603530883789},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.42032235860824585},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20200425386428833},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18338176608085632},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tc.2023.3329930","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2023.3329930","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"},{"id":"pmh:oai:cris.unibo.it:11585/956255","is_oa":false,"landing_page_url":"https://hdl.handle.net/11585/956255","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1890303118","https://openalex.org/W1967144452","https://openalex.org/W1970825693","https://openalex.org/W2035080386","https://openalex.org/W2044515661","https://openalex.org/W2107899848","https://openalex.org/W2765674462","https://openalex.org/W2768607776","https://openalex.org/W2893890288","https://openalex.org/W2905957440","https://openalex.org/W2907114372","https://openalex.org/W2921337991","https://openalex.org/W2946485102","https://openalex.org/W2949712929","https://openalex.org/W2962821792","https://openalex.org/W3013692244","https://openalex.org/W3049586678","https://openalex.org/W3094210834","https://openalex.org/W3105514082","https://openalex.org/W3130554079","https://openalex.org/W3136607342","https://openalex.org/W3137875211","https://openalex.org/W3207190350","https://openalex.org/W4211046602","https://openalex.org/W4285717907","https://openalex.org/W4295935130","https://openalex.org/W4302152450","https://openalex.org/W4319442925","https://openalex.org/W4382119943","https://openalex.org/W4386090486"],"related_works":["https://openalex.org/W116776481","https://openalex.org/W2125008614","https://openalex.org/W2039199837","https://openalex.org/W2926903444","https://openalex.org/W2612997776","https://openalex.org/W2378076731","https://openalex.org/W2051935741","https://openalex.org/W4286888643","https://openalex.org/W2784246983","https://openalex.org/W2763776149"],"abstract_inverted_index":{"Data":[0],"transfers":[1],"are":[2,15,25],"essential":[3],"in":[4,60,131,170,192],"today's":[5],"computing":[6],"systems":[7,174],"as":[8,109],"latency":[9,37],"and":[10,38,69,87,185],"complex":[11,44,104],"memory":[12,21],"access":[13,22,45],"patterns":[14,46,107],"increasingly":[16,61],"challenging":[17],"to":[18,28,47,97,142,149,188],"manage.":[19],"Direct":[20],"engines":[23],"(DMAES)":[24],"critically":[26],"needed":[27],"transfer":[29,106],"data":[30,105],"independently":[31],"of":[32,53,129,140,161],"the":[33,51,93,98,119,127],"processing":[34],"elements,":[35],"hiding":[36],"achieving":[39],"high":[40],"throughput":[41],"even":[42],"for":[43],"high-latency":[48],"memory.":[49],"With":[50],"prevalence":[52],"heterogeneous":[54],"systems,":[55,136],"DMAEs":[56],"must":[57],"operate":[58],"efficiently":[59],"diverse":[62],"environments.":[63],"This":[64],"work":[65],"proposes":[66],"a":[67,150,154],"modular":[68],"highly":[70],"configurable":[71],"open-source":[72],"DMAE":[73,178],"architecture":[74],"called":[75],"intelligent":[76],"DMA":[77],"(iDMA),":[78],"split":[79],"into":[80],"three":[81],"parts":[82],"that":[83],"can":[84],"be":[85],"composed":[86],"customized":[88],"independently.":[89],"The":[90,101,115],"front-end":[91],"implements":[92],"control":[94],"plane":[95],"binding":[96],"surrounding":[99],"system.":[100],"mid-end":[102],"accelerates":[103],"such":[108],"multi-dimensional":[110],"transfers,":[111],"scattering,":[112],"or":[113],"gathering.":[114],"back-end":[116],"interfaces":[117],"with":[118],"on-chip":[120],"communication":[121],"fabric":[122],"(data":[123],"plane).":[124],"We":[125,156,180],"assess":[126],"efficiency":[128],"iDMA":[130],"various":[132,193],"instantiations:":[133],"In":[134],"high-performance":[135],"we":[137],"achieve":[138,157],"speedups":[139],"up":[141],"15.8$\\boldsymbol{\\times}$with":[143],"only":[144],"1%":[145],"additional":[146],"area":[147,159],"compared":[148],"base":[151],"system":[152],"without":[153],"DMAE.":[155],"an":[158,176],"reduction":[160],"10%":[162],"while":[163],"improving":[164],"ML":[165],"inference":[166],"performance":[167,186],"by":[168],"23%":[169],"ultra-low-energy":[171],"edge":[172],"AI":[173],"over":[175],"existing":[177],"solution.":[179],"provide":[181],"area,":[182],"timing,":[183],"latency,":[184],"characterization":[187],"guide":[189],"its":[190],"instantiation":[191],"systems.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
