{"id":"https://openalex.org/W3156437603","doi":"https://doi.org/10.1145/3445814.3446703","title":"DiAG: a dataflow-inspired architecture for general-purpose processors","display_name":"DiAG: a dataflow-inspired architecture for general-purpose processors","publication_year":2021,"publication_date":"2021-04-11","ids":{"openalex":"https://openalex.org/W3156437603","doi":"https://doi.org/10.1145/3445814.3446703","mag":"3156437603"},"language":"en","primary_location":{"id":"doi:10.1145/3445814.3446703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445814.3446703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","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/A5011958785","display_name":"Dong Kai Wang","orcid":"https://orcid.org/0000-0002-6607-8869"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dong Kai Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011958785"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.4088,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79565418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9994000196456909,"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":0.8699803352355957},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7623971104621887},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.6678042411804199},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6417554616928101},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5790959000587463},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.5586679577827454},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5524755716323853},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.5508171319961548},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.5157904624938965},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.49936819076538086},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4982461929321289},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.48920679092407227},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.48472949862480164},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4050294756889343},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2684164047241211},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.1733938455581665}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699803352355957},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7623971104621887},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.6678042411804199},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6417554616928101},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5790959000587463},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.5586679577827454},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5524755716323853},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.5508171319961548},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.5157904624938965},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.49936819076538086},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4982461929321289},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.48920679092407227},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.48472949862480164},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4050294756889343},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2684164047241211},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.1733938455581665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3445814.3446703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3445814.3446703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2210378499","display_name":null,"funder_award_id":"1705047","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1830944699","https://openalex.org/W1969529818","https://openalex.org/W1970227175","https://openalex.org/W1984527041","https://openalex.org/W2002549773","https://openalex.org/W2006312753","https://openalex.org/W2024122052","https://openalex.org/W2031144446","https://openalex.org/W2059385825","https://openalex.org/W2089984858","https://openalex.org/W2090068045","https://openalex.org/W2095667776","https://openalex.org/W2101536355","https://openalex.org/W2117549828","https://openalex.org/W2119511297","https://openalex.org/W2122056310","https://openalex.org/W2128928939","https://openalex.org/W2133834148","https://openalex.org/W2142501475","https://openalex.org/W2147657366","https://openalex.org/W2149815585","https://openalex.org/W2152839228","https://openalex.org/W2154332652","https://openalex.org/W2161864047","https://openalex.org/W2167556016","https://openalex.org/W2169339215","https://openalex.org/W2170382128","https://openalex.org/W2170585292","https://openalex.org/W2177082073","https://openalex.org/W2289252105","https://openalex.org/W2935480346","https://openalex.org/W2950017407","https://openalex.org/W2953212265","https://openalex.org/W2998570630","https://openalex.org/W4239997146","https://openalex.org/W4241135198","https://openalex.org/W4242368470","https://openalex.org/W4245874061","https://openalex.org/W4252610065"],"related_works":["https://openalex.org/W2109400628","https://openalex.org/W2039534605","https://openalex.org/W2334517886","https://openalex.org/W3010737839","https://openalex.org/W4246048158","https://openalex.org/W4301270406","https://openalex.org/W1985734101","https://openalex.org/W2562747857","https://openalex.org/W2186678163","https://openalex.org/W2523292611"],"abstract_inverted_index":{"The":[0],"end":[1],"of":[2,7,14,21,28,31,124,135,145],"Dennard":[3],"scaling":[4],"and":[5,48,163,178,184,193,206],"decline":[6],"Moore's":[8],"law":[9],"has":[10,52],"prompted":[11],"the":[12,26,36,39,122,125,136,143,173,190],"proliferation":[13],"hardware":[15],"accelerators":[16],"for":[17,56],"a":[18,80,168,203],"wide":[19],"range":[20],"application":[22],"domains.":[23],"Yet,":[24],"at":[25],"dawn":[27],"an":[29,61,213],"era":[30],"specialized":[32,112],"computing,":[33],"left":[34],"behind":[35],"trend":[37],"is":[38,43,101,121],"general-purpose":[40,82],"processor":[41,83],"that":[42,85,131,171],"still":[44],"most":[45],"easily":[46],"programmed":[47],"widely":[49],"used":[50],"but":[51],"seen":[53],"incremental":[54],"changes":[55],"decades.":[57],"This":[58],"work":[59],"uses":[60],"accelerator-inspired":[62],"approach":[63],"to":[64,68,103,118],"rethink":[65],"CPU":[66,216],"microarchitecture":[67],"improve":[69],"its":[70,75,180],"energy":[71,210],"efficiency":[72,211],"while":[73],"retaining":[74],"generality.":[76],"We":[77,166],"propose":[78],"DiAG,":[79],"dataflow-based":[81],"architecture":[84,120],"can":[86],"minimize":[87],"latency":[88],"by":[89,96],"exploiting":[90,97],"instruction-level":[91],"parallelism":[92],"or":[93,115],"maximize":[94],"throughput":[95],"data-level":[98],"parallelism.":[99],"DiAG":[100,148,169,197],"designed":[102],"support":[104],"any":[105],"RISC-like":[106],"instruction":[107,161],"set":[108],"without":[109],"explicitly":[110],"requiring":[111],"languages,":[113],"libraries,":[114],"compilers.":[116],"Central":[117],"this":[119],"abstraction":[123],"register":[126,129],"file":[127],"as":[128],"'lanes'":[130],"allow":[132],"implicit":[133],"construction":[134],"program's":[137],"dataflow":[138],"graph":[139],"in":[140,176,209],"hardware.":[141],"At":[142],"cost":[144],"increased":[146],"area,":[147],"offers":[149],"three":[150],"main":[151],"benefits":[152],"over":[153],"conventional":[154],"out-of-order":[155,215],"microarchitectures:":[156],"reduced":[157],"front-end":[158],"overhead,":[159],"efficient":[160],"reuse,":[162],"thread-level":[164],"pipelining.":[165],"implement":[167],"prototype":[170],"supports":[172],"RISC-V":[174],"ISA":[175],"SystemVerilog":[177],"evaluate":[179],"performance,":[181],"power":[182],"consumption,":[183],"area":[185],"with":[186,199],"EDA":[187],"tools.":[188],"In":[189],"tested":[191],"Rodinia":[192],"SPEC":[194],"CPU2017":[195],"benchmarks,":[196],"configured":[198],"512":[200],"PEs":[201],"achieves":[202],"1.18x":[204],"speedup":[205],"1.63x":[207],"improvement":[208],"against":[212],"aggressive":[214],"baseline.":[217]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}