{"id":"https://openalex.org/W4200594740","doi":"https://doi.org/10.1109/jssc.2021.3134897","title":"DPU: DAG Processing Unit for Irregular Graphs With Precision-Scalable Posit Arithmetic in 28 nm","display_name":"DPU: DAG Processing Unit for Irregular Graphs With Precision-Scalable Posit Arithmetic in 28 nm","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4200594740","doi":"https://doi.org/10.1109/jssc.2021.3134897"},"language":"en","primary_location":{"id":"doi:10.1109/jssc.2021.3134897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2021.3134897","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.05660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082391782","display_name":"Nimish Shah","orcid":"https://orcid.org/0000-0003-3234-0715"},"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":"Nimish Shah","raw_affiliation_strings":["Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083132017","display_name":"Laura Isabel Galindez Olascoaga","orcid":"https://orcid.org/0000-0001-8601-5024"},"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"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["BE","US"],"is_corresponding":false,"raw_author_name":"Laura Isabel Galindez Olascoaga","raw_affiliation_strings":["Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium","Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090482289","display_name":"Shirui Zhao","orcid":"https://orcid.org/0000-0003-4280-0578"},"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":"Shirui Zhao","raw_affiliation_strings":["Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074451226","display_name":"Wannes Meert","orcid":"https://orcid.org/0000-0001-9560-3872"},"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":"Wannes Meert","raw_affiliation_strings":["DTAI, Department of Computer Science, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"DTAI, Department of Computer Science, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"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":["Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, MICAS Laboratories, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082391782"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":2.346,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89222942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"57","issue":"8","first_page":"2586","last_page":"2596"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9994000196456909,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9975000023841858,"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/scalability","display_name":"Scalability","score":0.6730791926383972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6480568647384644},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6126810908317566},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.5387414693832397},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4467836916446686},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.41661909222602844},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3249322474002838},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2591021955013275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2019612193107605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13672959804534912},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10340195894241333}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6730791926383972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480568647384644},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6126810908317566},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.5387414693832397},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4467836916446686},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.41661909222602844},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3249322474002838},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2591021955013275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2019612193107605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13672959804534912},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10340195894241333},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jssc.2021.3134897","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jssc.2021.3134897","pdf_url":null,"source":{"id":"https://openalex.org/S83637746","display_name":"IEEE Journal of Solid-State Circuits","issn_l":"0018-9200","issn":["0018-9200","1558-173X"],"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 Journal of Solid-State Circuits","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/688132","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/688132","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ieee Journal Of Solid-State Circuits, vol. 57 (8), (1-11)","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2112.05660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.05660","pdf_url":"https://arxiv.org/pdf/2112.05660","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.05660","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.05660","pdf_url":"https://arxiv.org/pdf/2112.05660","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1000079846","display_name":null,"funder_award_id":"ERC-2016-STG-715037","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1520511539","https://openalex.org/W1955594754","https://openalex.org/W2035080386","https://openalex.org/W2040370888","https://openalex.org/W2067354926","https://openalex.org/W2080090223","https://openalex.org/W2101005153","https://openalex.org/W2132022337","https://openalex.org/W2140191557","https://openalex.org/W2181846018","https://openalex.org/W2612094043","https://openalex.org/W2743322459","https://openalex.org/W2746349752","https://openalex.org/W2790925711","https://openalex.org/W2891677407","https://openalex.org/W2904906706","https://openalex.org/W2907724310","https://openalex.org/W2908782257","https://openalex.org/W2922398414","https://openalex.org/W2946077262","https://openalex.org/W2948396960","https://openalex.org/W2963708377","https://openalex.org/W2980270412","https://openalex.org/W2987129023","https://openalex.org/W3003174489","https://openalex.org/W3036028067","https://openalex.org/W3040024858","https://openalex.org/W3043110088","https://openalex.org/W3114479342","https://openalex.org/W3120740533","https://openalex.org/W3152828401","https://openalex.org/W3159481662","https://openalex.org/W3174644278","https://openalex.org/W4236868170","https://openalex.org/W4241140669","https://openalex.org/W6685981158","https://openalex.org/W6740705323","https://openalex.org/W6762675705","https://openalex.org/W6767162966","https://openalex.org/W6795880318"],"related_works":["https://openalex.org/W4302345037","https://openalex.org/W2731094954","https://openalex.org/W2789273959","https://openalex.org/W1998712144","https://openalex.org/W2952978498","https://openalex.org/W4292730466","https://openalex.org/W4401278057","https://openalex.org/W2914790213","https://openalex.org/W2063186542","https://openalex.org/W3141650078"],"abstract_inverted_index":{"Computation":[0],"in":[1,29,42,123,190],"several":[2],"real-world":[3],"applications":[4],"such":[5],"as":[6,19,177],"probabilistic":[7,160],"machine":[8,161],"learning,":[9],"sparse":[10,156],"linear":[11,157],"algebra,":[12],"and":[13,39,95,138,150,159,181,187,209,222],"robotic":[14],"navigation":[15],"can":[16,85],"be":[17],"modeled":[18],"irregular":[20,26,64,234],"directed":[21],"acyclic":[22],"graphs":[23],"(DAGs).":[24],"The":[25,66,83,118],"data":[27],"dependencies":[28],"DAGs":[30,154],"pose":[31],"challenges":[32],"to":[33,101,114,179],"parallel":[34,71],"execution":[35,62,232],"on":[36,153],"general-purpose":[37],"CPUs":[38],"GPUs,":[40],"resulting":[41,189],"severe":[43],"under-utilization":[44],"of":[45,63,79,129,155,174,184,194,233],"the":[46,60,185,220],"hardware.":[47],"This":[48,164],"article":[49],"proposes":[50],"DAG":[51,81,235],"Processing":[52],"Unit":[53],"(DPU),":[54],"a":[55,80,88,91,102,107,127,171,191],"specialized":[56,227],"processor":[57],"designed":[58],"for":[59],"efficient":[61,99],"DAGs.":[65],"DPU":[67,119,229],"is":[68,112,120,166,200],"equipped":[69],"with":[70,197,226],"compute":[72],"units":[73],"(CUs)":[74],"that":[75],"execute":[76],"different":[77],"subgraphs":[78],"independently.":[82],"CUs":[84],"synchronize":[86],"within":[87],"cycle":[89],"using":[90],"hardware-supported":[92],"synchronization":[93],"primitive":[94],"communicate":[96],"via":[97],"an":[98],"interconnect":[100],"global":[103],"banked":[104],"scratchpad.":[105],"Furthermore,":[106],"precision-scalable":[108],"positTrademarked.":[109],"arithmetic":[110],"unit":[111],"developed":[113],"enable":[115],"application-dependent":[116],"precision.":[117],"taped":[121],"out":[122],"28-nm":[124],"CMOS,":[125],"achieving":[126],"speedup":[128],"5.1":[130],"<inline-formula":[131,140,202,211],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[132,141,203,212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[133,142,204,213],"<tex-math":[134,143,205,214],"notation=\"LaTeX\">$\\times":[135,144,206,215],"$":[136,145,207,216],"</tex-math></inline-formula>":[137,146,208,217],"20.6":[139],"over":[147],"state-of-the-art":[148],"CPU":[149,186,221],"GPU":[151],"implementations":[152],"algebra":[158],"learning":[162],"workloads.":[163,236],"performance":[165],"achieved":[167],"while":[168],"operating":[169],"at":[170],"power":[172],"budget":[173],"0.23":[175],"W,":[176],"opposed":[178],"55":[180],"98":[182],"W":[183],"GPU,":[188,223],"peak":[192],"efficiency":[193],"538":[195],"GOPS/W":[196],"DPU,":[198],"which":[199],"1350":[201],"9000":[210],"higher":[218],"than":[219],"respectively.":[224],"Thus,":[225],"architecture,":[228],"enables":[230],"low-power":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
