{"id":"https://openalex.org/W3186615785","doi":"https://doi.org/10.23919/vlsicircuits52068.2021.9492517","title":"PETRA: A 22nm 6.97TFLOPS/W AIB-Enabled Configurable Matrix and Convolution Accelerator Integrated with an Intel Stratix 10 FPGA","display_name":"PETRA: A 22nm 6.97TFLOPS/W AIB-Enabled Configurable Matrix and Convolution Accelerator Integrated with an Intel Stratix 10 FPGA","publication_year":2021,"publication_date":"2021-06-13","ids":{"openalex":"https://openalex.org/W3186615785","doi":"https://doi.org/10.23919/vlsicircuits52068.2021.9492517","mag":"3186615785"},"language":"en","primary_location":{"id":"doi:10.23919/vlsicircuits52068.2021.9492517","is_oa":false,"landing_page_url":"https://doi.org/10.23919/vlsicircuits52068.2021.9492517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Symposium on VLSI Circuits","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/A5011111894","display_name":"Sung-Gun Cho","orcid":"https://orcid.org/0000-0001-6934-6956"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]},{"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":true,"raw_author_name":"Sung-Gun Cho","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,USA","University of Michigan, Ann Arbor, MI, USA","Intel Corporation, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Intel Corporation, San Jose, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063342536","display_name":"Wei Tang","orcid":"https://orcid.org/0000-0001-5204-9728"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Tang","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,USA","University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041944874","display_name":"Chester Liu","orcid":"https://orcid.org/0000-0003-0115-9630"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chester Liu","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,USA","University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038110244","display_name":"Zhengya Zhang","orcid":"https://orcid.org/0000-0001-5963-9018"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengya Zhang","raw_affiliation_strings":["University of Michigan,Ann Arbor,MI,USA","University of Michigan, Ann Arbor, MI, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Ann Arbor,MI,USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011111894"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.6908,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66266961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9988999962806702,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stratix","display_name":"Stratix","score":0.8590037822723389},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7253813743591309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6022390723228455},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5065246820449829},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4902239441871643},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44260403513908386},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4379359483718872},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4252765476703644},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3363823890686035},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3362271785736084},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15815365314483643},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.14322960376739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07615655660629272}],"concepts":[{"id":"https://openalex.org/C2776277307","wikidata":"https://www.wikidata.org/wiki/Q22074755","display_name":"Stratix","level":3,"score":0.8590037822723389},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7253813743591309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6022390723228455},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5065246820449829},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4902239441871643},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44260403513908386},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4379359483718872},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4252765476703644},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3363823890686035},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3362271785736084},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15815365314483643},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.14322960376739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07615655660629272},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/vlsicircuits52068.2021.9492517","is_oa":false,"landing_page_url":"https://doi.org/10.23919/vlsicircuits52068.2021.9492517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Symposium on VLSI Circuits","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":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1509155667","https://openalex.org/W2518118925","https://openalex.org/W3208151864","https://openalex.org/W2353466882","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W1564576805","https://openalex.org/W1488776355","https://openalex.org/W4244262766","https://openalex.org/W2102495623"],"abstract_inverted_index":{"PETRA":[0,20,53,76],"is":[1,21,77],"a":[2,31,70,86],"configurable":[3,32],"FP16":[4],"matrix":[5],"multiplication":[6,60],"and":[7,40,62,67,96,99],"convolution":[8,63],"accelerator":[9],"designed":[10],"to":[11,35,45,90],"be":[12],"2.5D":[13],"integrated":[14,78],"using":[15],"Advanced":[16],"Interface":[17],"Bus":[18],"(AIB).":[19],"built":[22],"upon":[23],"four":[24],"16\u00d716":[25],"systolic":[26],"arrays,":[27],"but":[28],"it":[29,68],"employs":[30],"H-tree":[33],"accumulation":[34],"improve":[36],"both":[37],"the":[38,41,92,97],"latency":[39],"utilization":[42],"by":[43],"up":[44],"8\u00d7.":[46],"A":[47],"22nm":[48],"3.04mm":[49],"<sup":[50],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[51],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[52],"prototype":[54],"provides":[55],"1.433TFLOPS":[56],"in":[57,85],"computing":[58],"matrix-matrix":[59],"(MMM)":[61],"(conv)":[64],"at":[65,74],"0.88V,":[66],"achieves":[69],"6.97TFLOPS/W":[71],"peak":[72],"efficiency":[73,100],"0.7V.":[75],"with":[79],"an":[80],"Intel":[81],"Stratix":[82],"10":[83],"FPGA":[84,95],"multi-chip":[87],"package":[88],"(MCP)":[89],"provide":[91],"flexibility":[93],"of":[94,101],"performance":[98],"PETRA.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}