{"id":"https://openalex.org/W3212852614","doi":"https://doi.org/10.1109/dac18074.2021.9586257","title":"RASA: Efficient Register-Aware Systolic Array Matrix Engine for CPU","display_name":"RASA: Efficient Register-Aware Systolic Array Matrix Engine for CPU","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3212852614","doi":"https://doi.org/10.1109/dac18074.2021.9586257","mag":"3212852614"},"language":"en","primary_location":{"id":"doi:10.1109/dac18074.2021.9586257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5069792279","display_name":"Geonhwa Jeong","orcid":"https://orcid.org/0000-0001-6659-3927"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geonhwa Jeong","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064436855","display_name":"Eric Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Qin","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007782265","display_name":"Ananda Samajdar","orcid":"https://orcid.org/0000-0003-0046-3745"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananda Samajdar","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024082060","display_name":"Christopher J. Hughes","orcid":"https://orcid.org/0009-0009-2888-0314"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. Hughes","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036799188","display_name":"Sreenivas Subramoney","orcid":"https://orcid.org/0000-0001-5372-0173"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreenivas Subramoney","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034089074","display_name":"Tushar Krishna","orcid":"https://orcid.org/0000-0001-5738-6942"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Krishna","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"258"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.996999979019165,"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/datapath","display_name":"Datapath","score":0.8788557648658752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262673377990723},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.6786444187164307},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.6614519357681274},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5959633588790894},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4826681911945343},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.43119752407073975},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.36925268173217773},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32883501052856445},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32293248176574707},{"id":"https://openalex.org/keywords/very-large-scale-integration","display_name":"Very-large-scale integration","score":0.2792501747608185},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.1861482560634613}],"concepts":[{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.8788557648658752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262673377990723},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.6786444187164307},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.6614519357681274},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5959633588790894},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4826681911945343},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.43119752407073975},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.36925268173217773},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32883501052856445},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32293248176574707},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.2792501747608185},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.1861482560634613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18074.2021.9586257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2442974303","https://openalex.org/W2606722458","https://openalex.org/W2790925711","https://openalex.org/W2896457183","https://openalex.org/W2931743911","https://openalex.org/W2947737663","https://openalex.org/W2963341956","https://openalex.org/W3042343931","https://openalex.org/W3097528158","https://openalex.org/W3116917247","https://openalex.org/W6755207826","https://openalex.org/W6763737044","https://openalex.org/W6787944248"],"related_works":["https://openalex.org/W2115178757","https://openalex.org/W2094874787","https://openalex.org/W3013048777","https://openalex.org/W2024145214","https://openalex.org/W1580556151","https://openalex.org/W2144463068","https://openalex.org/W2185915791","https://openalex.org/W2129565950","https://openalex.org/W2228485673","https://openalex.org/W2120705320"],"abstract_inverted_index":{"As":[0],"AI-based":[1],"applications":[2],"become":[3],"pervasive,":[4],"CPU":[5],"vendors":[6],"are":[7],"starting":[8],"to":[9,16,47,51,73,84],"incorporate":[10],"matrix":[11,28],"engines":[12,29],"within":[13],"the":[14,23,53,59],"datapath":[15],"boost":[17],"efficiency.":[18],"Systolic":[19,68],"arrays":[20],"have":[21],"been":[22],"premier":[24],"architectural":[25],"choice":[26],"as":[27],"in":[30],"offload":[31],"accelerators.":[32],"However,":[33],"we":[34,64],"demonstrate":[35],"that":[36],"incorporating":[37],"them":[38,89],"inside":[39],"CPUs":[40],"can":[41],"introduce":[42],"under-utilization":[43],"and":[44,55,81,87,99],"stalls":[45],"due":[46],"limited":[48],"register":[49],"storage":[50],"amortize":[52],"fill":[54],"drain":[56],"times":[57],"of":[58],"array.":[60],"To":[61],"address":[62],"this,":[63],"propose":[65],"RASA,":[66],"Register-Aware":[67],"Array.":[69],"We":[70],"develop":[71],"techniques":[72],"divide":[74],"an":[75],"execution":[76],"stage":[77],"into":[78],"several":[79],"sub-stages":[80],"overlap":[82],"instructions":[83],"hide":[85],"overheads":[86],"run":[88],"concurrently.":[90],"RASA-based":[91],"designs":[92],"improve":[93],"performance":[94],"significantly":[95],"with":[96],"negligible":[97],"area":[98],"power":[100],"overhead.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
