{"id":"https://openalex.org/W4392450754","doi":"https://doi.org/10.1109/lca.2024.3371062","title":"Exploiting Direct Memory Operands in GPU Instructions","display_name":"Exploiting Direct Memory Operands in GPU Instructions","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392450754","doi":"https://doi.org/10.1109/lca.2024.3371062"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2024.3371062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2024.3371062","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5079792822","display_name":"Ali Mohammadpur-Fard","orcid":"https://orcid.org/0000-0001-8371-2828"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Ali Mohammadpur-Fard","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072312467","display_name":"Sina Darabi","orcid":"https://orcid.org/0000-0002-7082-123X"},"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/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]},{"id":"https://openalex.org/I57201433","display_name":"Universit\u00e0 della Svizzera italiana","ror":"https://ror.org/03c4atk17","country_code":"CH","type":"education","lineage":["https://openalex.org/I57201433"]},{"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":["CH","ES","IR"],"is_corresponding":false,"raw_author_name":"Sina Darabi","raw_affiliation_strings":["School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","Barcelona Supercomputing Center (BSC), Barcelona, Spain","Faculty of Informatics, Universita della Svizzera Italiana (USI), Lugano, Switzerland"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]},{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC), Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Faculty of Informatics, Universita della Svizzera Italiana (USI), Lugano, Switzerland","institution_ids":["https://openalex.org/I57201433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048190","display_name":"Hajar Falahati","orcid":"https://orcid.org/0000-0001-8375-3339"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hajar Falahati","raw_affiliation_strings":["School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053374807","display_name":"Negin Mahani","orcid":"https://orcid.org/0000-0001-5232-3539"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]},{"id":"https://openalex.org/I115566878","display_name":"Shahid Bahonar University of Kerman","ror":"https://ror.org/04zn42r77","country_code":"IR","type":"education","lineage":["https://openalex.org/I115566878"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Negin Mahani","raw_affiliation_strings":["School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","Department of Computer Engineering, Higher Education Complex of Zarand, Shahid Bahonar University, Kerman, Iran"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]},{"raw_affiliation_string":"Department of Computer Engineering, Higher Education Complex of Zarand, Shahid Bahonar University, Kerman, Iran","institution_ids":["https://openalex.org/I115566878"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040238844","display_name":"Hamid Sarbazi\u2010Azad","orcid":"https://orcid.org/0000-0003-4079-8603"},"institutions":[{"id":"https://openalex.org/I4210146419","display_name":"Institute for Research in Fundamental Sciences","ror":"https://ror.org/04xreqs31","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210146419"]},{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hamid Sarbazi-Azad","raw_affiliation_strings":["Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]},{"raw_affiliation_string":"School of Computer Science, Institute for Researches in Fundamental Sciences (IPM), Tehran, Iran","institution_ids":["https://openalex.org/I4210146419"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5079792822"],"corresponding_institution_ids":["https://openalex.org/I133529467"],"apc_list":null,"apc_paid":null,"fwci":1.5557,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80691679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"23","issue":"2","first_page":"162","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9940000176429749,"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":0.9940000176429749,"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":0.9277999997138977,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9168000221252441,"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/operand","display_name":"Operand","score":0.8717300295829773},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8248879909515381},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6562709212303162},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4310092329978943},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.19932454824447632}],"concepts":[{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.8717300295829773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248879909515381},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6562709212303162},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4310092329978943},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.19932454824447632}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2024.3371062","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2024.3371062","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":17,"referenced_works":["https://openalex.org/W1997162567","https://openalex.org/W2080592089","https://openalex.org/W2128120785","https://openalex.org/W2181600388","https://openalex.org/W2238992335","https://openalex.org/W2273440736","https://openalex.org/W2588318436","https://openalex.org/W2755395451","https://openalex.org/W2884590322","https://openalex.org/W3100327344","https://openalex.org/W3102510044","https://openalex.org/W3206857466","https://openalex.org/W4237024478","https://openalex.org/W4238862414","https://openalex.org/W4253306330","https://openalex.org/W4360831990","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2556282987","https://openalex.org/W1533508804","https://openalex.org/W2050923821","https://openalex.org/W2506885233","https://openalex.org/W1970370079","https://openalex.org/W2333680585","https://openalex.org/W2098637578","https://openalex.org/W1999746819","https://openalex.org/W2055541046"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"are":[2,54],"widely":[3],"used":[4,56,90],"for":[5],"diverse":[6],"applications,":[7],"particularly":[8],"data-parallel":[9],"tasks":[10],"like":[11],"machine":[12],"learning":[13],"and":[14,96,128],"scientific":[15],"computing.":[16],"However,":[17],"their":[18],"efficiency":[19],"is":[20],"hindered":[21],"by":[22,108,126,132],"architectural":[23],"limitations,":[24],"inherited":[25],"from":[26],"historical":[27],"RISC":[28],"processors,":[29],"in":[30,50,82,119],"handling":[31],"memory":[32,80,117],"loads":[33,114],"causing":[34],"high":[35],"register":[36,52,67,85],"file":[37,53,68,86],"contention.":[38],"We":[39],"observe":[40],"that":[41],"a":[42,104],"significant":[43],"number":[44],"(around":[45],"26%)":[46],"of":[47,64,78],"values":[48,81,89],"present":[49],"the":[51,65,76,83],"typically":[55],"only":[57,91],"once,":[58],"contributing":[59],"to":[60],"more":[61],"than":[62],"25%":[63],"total":[66],"bank":[69],"conflicts,":[70],"on":[71,134],"average.":[72],"This":[73],"paper":[74],"addresses":[75],"challenge":[77],"single-use":[79,113],"GPU":[84],"(i.e.":[87],"data":[88],"once)":[92],"which":[93],"wastes":[94],"space":[95],"increases":[97],"latency.":[98],"To":[99],"this":[100],"end,":[101],"we":[102],"introduce":[103],"novel":[105],"mechanism":[106],"inspired":[107],"CISC":[109],"architectures.":[110],"It":[111],"replaces":[112],"with":[115,136],"direct":[116],"operands":[118],"arithmetic":[120],"operations.":[121],"Our":[122],"approach":[123],"improves":[124],"performance":[125],"20%":[127],"reduces":[129],"energy":[130],"consumption":[131],"18%,":[133],"average,":[135],"negligible":[137],"(<1%)":[138],"hardware":[139],"overhead.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}