{"id":"https://openalex.org/W1980884328","doi":"https://doi.org/10.1109/hpca.2010.5463057","title":"DMA++: on the fly data realignment for on-chip memories","display_name":"DMA++: on the fly data realignment for on-chip memories","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1980884328","doi":"https://doi.org/10.1109/hpca.2010.5463057","mag":"1980884328"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2010.5463057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2010.5463057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture","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/A5058360486","display_name":"Nikola Vuji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nikola Vujic","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Barcelona Supercomputing Center,Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036427962","display_name":"Marc Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-3780-1106"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Gonzalez","raw_affiliation_strings":["Iniversitat Politecnica de Catalunya, Barcelona, Spain","Universitat Polit\u00e8cnica de Catalunya, Barcelona  Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iniversitat Politecnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona  Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026623616","display_name":"Felipe Cabarcas","orcid":"https://orcid.org/0000-0002-8966-0405"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I35961687","display_name":"Universidad de Antioquia","ror":"https://ror.org/03bp5hc83","country_code":"CO","type":"education","lineage":["https://openalex.org/I35961687"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["CO","ES"],"is_corresponding":false,"raw_author_name":"Felipe Cabarcas","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Universidad de Antioquia, Medellin, Colombia","Universidad de Antioqu\u00eda, Medell\u00edn. Colombia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Universidad de Antioquia, Medellin, Colombia","institution_ids":["https://openalex.org/I35961687"]},{"raw_affiliation_string":"Universidad de Antioqu\u00eda, Medell\u00edn. Colombia","institution_ids":["https://openalex.org/I35961687"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082472991","display_name":"Alex Ram\u00edrez","orcid":"https://orcid.org/0000-0003-3317-4616"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Alex Ramirez","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Barcelona Supercomputing Center,Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074097057","display_name":"Xavier Martorell","orcid":"https://orcid.org/0000-0002-0417-3430"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Martorell","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Barcelona Supercomputing Center,Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075755125","display_name":"Eduard Ayguad\u00e9","orcid":"https://orcid.org/0000-0002-5146-103X"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduard Ayguade","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain","Barcelona Supercomputing Center,Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.506,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65037175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9994999766349792,"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":0.8771352767944336},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8030742406845093},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7815462946891785},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5034028887748718},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48954710364341736},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45348402857780457},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4421325922012329},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43142393231391907},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.42685556411743164},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4231027662754059},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.42222753167152405},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.38551270961761475},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32185620069503784},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31452882289886475},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2105909287929535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8771352767944336},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8030742406845093},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7815462946891785},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5034028887748718},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48954710364341736},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45348402857780457},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4421325922012329},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43142393231391907},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.42685556411743164},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4231027662754059},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.42222753167152405},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.38551270961761475},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32185620069503784},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31452882289886475},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2105909287929535},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca.2010.5463057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2010.5463057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W127897580","https://openalex.org/W1791189328","https://openalex.org/W2005343162","https://openalex.org/W2051598123","https://openalex.org/W2059807497","https://openalex.org/W2079726719","https://openalex.org/W2079834329","https://openalex.org/W2099404643","https://openalex.org/W2109122299","https://openalex.org/W2110288503","https://openalex.org/W2127324789","https://openalex.org/W2137249790","https://openalex.org/W2137296754","https://openalex.org/W2143795231","https://openalex.org/W2144643978","https://openalex.org/W2148701871","https://openalex.org/W2156139954","https://openalex.org/W2159535674","https://openalex.org/W2166128308","https://openalex.org/W2169150396","https://openalex.org/W3152387986","https://openalex.org/W4242539338","https://openalex.org/W4247913514","https://openalex.org/W6605292869","https://openalex.org/W6670344032","https://openalex.org/W6680703539","https://openalex.org/W6681610370"],"related_works":["https://openalex.org/W2162270818","https://openalex.org/W2994245508","https://openalex.org/W4242172182","https://openalex.org/W2082875307","https://openalex.org/W4237780868","https://openalex.org/W4285302443","https://openalex.org/W1998013902","https://openalex.org/W2127594310","https://openalex.org/W2137845512","https://openalex.org/W2019451907"],"abstract_inverted_index":{"Multimedia":[0],"extensions":[1],"based":[2],"on":[3,125],"Single-Instruction":[4],"Multiple-Data":[5],"(SIMD)":[6],"units":[7,27],"are":[8,11],"widespread.":[9],"They":[10],"used":[12],"both":[13],"in":[14,34,55,92,111,138],"processors":[15],"and":[16,40,79,132],"accelerators":[17,112],"(e.g.,":[18],"the":[19,45,48,52,56,59,65,72,90,107,117,126,135,139,147,154,176,179,186,189],"Cell":[20],"SPEs),":[21],"since":[22],"some":[23],"time":[24],"ago.":[25],"SIMD":[26],"have":[28],"usually":[29],"big":[30],"memory":[31,77],"alignment":[32,67,137],"constraints":[33],"order":[35],"to":[36,88,163,198],"meet":[37],"power":[38],"requirements":[39],"design":[41],"simplicity.":[42],"This":[43],"increases":[44],"complexity":[46],"of":[47,64,68,86,106,178,188],"code":[49,195],"generated":[50],"by":[51,128],"compiler,":[53],"as":[54],"general":[57],"case,":[58],"compiler":[60],"cannot":[61],"be":[62],"sure":[63],"proper":[66,136],"data.":[69],"For":[70],"that,":[71],"ISA":[73],"provides":[74],"either":[75],"unaligned":[76,205],"load":[78],"store":[80],"instructions,":[81],"or":[82],"a":[83,99],"special":[84,151],"set":[85],"instructions":[87],"perform":[89],"realignments":[91],"software.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97],"propose":[98],"hardware":[100],"realignment":[101,130],"unit":[102],"that":[103,172,193],"takes":[104],"advantage":[105],"DMA":[108,180],"transfers":[109,181],"needed":[110],"with":[113,134,149,168,173,202],"local":[114],"memories.":[115],"While":[116],"data":[118,148,155],"is":[119,123,156,182,196],"being":[120],"transferred,":[121],"it":[122],"realigned":[124,157],"fly":[127],"our":[129,174],"unit,":[131],"stored":[133],"accelerator":[140,143],"memory.":[141,165],"The":[142],"can":[144],"then":[145],"access":[146],"no":[150],"instructions.":[152],"Finally,":[153],"properly":[158],"also":[159],"when":[160],"put":[161],"back":[162],"main":[164],"Our":[166],"experiments":[167],"four":[169],"applications":[170],"show":[171],"approach,":[175],"bandwidth":[177],"not":[183],"penalized.":[184],"And":[185],"performance":[187],"synthetic":[190],"benchmarks":[191],"shows":[192],"aligned":[194],"1.5":[197],"2":[199],"times":[200],"better":[201],"respect":[203],"using":[204],"code.":[206]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
