{"id":"https://openalex.org/W4401879849","doi":"https://doi.org/10.1109/vlsitechnologyandcir46783.2024.10631322","title":"A 52.01 TFLOPS/W Diffusion Model Processor with Inter-Time-Step Convolution-Attention-Redundancy Elimination and Bipolar Floating-Point Multiplication","display_name":"A 52.01 TFLOPS/W Diffusion Model Processor with Inter-Time-Step Convolution-Attention-Redundancy Elimination and Bipolar Floating-Point Multiplication","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4401879849","doi":"https://doi.org/10.1109/vlsitechnologyandcir46783.2024.10631322"},"language":"en","primary_location":{"id":"doi:10.1109/vlsitechnologyandcir46783.2024.10631322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsitechnologyandcir46783.2024.10631322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and 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/A5071432313","display_name":"Yubin Qin","orcid":"https://orcid.org/0000-0001-5530-5416"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yubin Qin","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704992","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-1849-9319"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101975562","display_name":"Xiaolong Yang","orcid":"https://orcid.org/0009-0003-0105-8351"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Yang","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935571","display_name":"Zhiren Zhao","orcid":"https://orcid.org/0009-0007-6074-7324"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiren Zhao","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032344424","display_name":"Shaojun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596877","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0002-1759-5085"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054524841","display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0003-2309-572X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["Tsinghua University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5071432313"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.8675,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95703816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"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/T12810","display_name":"Real-time simulation and control systems","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9559000134468079,"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/T10320","display_name":"Neural Networks and Applications","score":0.954800009727478,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/redundancy","display_name":"Redundancy (engineering)","score":0.6590775847434998},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5949835777282715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5836033821105957},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5826705098152161},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5757753252983093},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43701690435409546},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.41556206345558167},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20221617817878723},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10964652895927429},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10765677690505981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1040915846824646},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1026446521282196},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08287885785102844}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6590775847434998},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5949835777282715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5836033821105957},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5826705098152161},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5757753252983093},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43701690435409546},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.41556206345558167},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20221617817878723},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10964652895927429},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10765677690505981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1040915846824646},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1026446521282196},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08287885785102844},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vlsitechnologyandcir46783.2024.10631322","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsitechnologyandcir46783.2024.10631322","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Symposium on VLSI Technology and Circuits (VLSI Technology and Circuits)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5299999713897705,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8978128402","display_name":null,"funder_award_id":"62125403,92164301,62304121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4237941542"],"related_works":["https://openalex.org/W3093936885","https://openalex.org/W2994146737","https://openalex.org/W295308437","https://openalex.org/W2992046671","https://openalex.org/W2017990332","https://openalex.org/W2080337923","https://openalex.org/W1488776355","https://openalex.org/W2093251826","https://openalex.org/W4221155546","https://openalex.org/W4244262766"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"energy-efficient":[4],"diffusion":[5],"model":[6],"processor":[7],"exploiting":[8],"inter-time-step":[9],"computation":[10,42],"redundancy.":[11],"It":[12,65],"has":[13],"three":[14],"features:":[15],"1)":[16],"a":[17,31,47,67],"semantic-segment":[18],"sparse":[19],"convolution":[20,26],"engine":[21],"removes":[22],"88.5%":[23],"of":[24,70],"duplicated":[25],"layer":[27,40],"(CL)":[28],"computations.":[29],"2)":[30],"resemble":[32],"trivial":[33],"attention":[34,39],"exponent":[35],"inheritance":[36],"design":[37],"improves":[38],"(AL)":[41],"efficiency":[43,69],"by":[44,55,75],"16.7\u00d7.":[45],"3)":[46],"bipolar":[48],"floating-point":[49],"multiplier":[50],"saves":[51],"25.4%":[52],"multiplication":[53,59],"effort":[54],"avoiding":[56],"ineffective":[57],"mantissa":[58],"for":[60],"both":[61],"CL":[62,82],"and":[63,72,77,83],"AL.":[64],"achieves":[66],"peak":[68],"52.01TFLOPS/W,":[71],"reduces":[73],"energy":[74],"23.14\u00d7":[76],"3.94\u00d7":[78],"compared":[79],"to":[80],"state-of-the-art":[81],"AL":[84],"processors.":[85]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}