{"id":"https://openalex.org/W2979365412","doi":"https://doi.org/10.1145/3355606","title":"The Next 700 Accelerated Layers","display_name":"The Next 700 Accelerated Layers","publication_year":2019,"publication_date":"2019-10-11","ids":{"openalex":"https://openalex.org/W2979365412","doi":"https://doi.org/10.1145/3355606","mag":"2979365412"},"language":"en","primary_location":{"id":"doi:10.1145/3355606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355606","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355606","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3355606","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017292577","display_name":"Nicolas Vasilache","orcid":"https://orcid.org/0000-0002-4096-3325"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Nicolas Vasilache","raw_affiliation_strings":["Facebook AI Research, NY, USA","Facebook AI Research [New York]"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, NY, USA","institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"raw_affiliation_string":"Facebook AI Research [New York]","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034245897","display_name":"Oleksandr Zinenko","orcid":"https://orcid.org/0000-0003-1978-0222"},"institutions":[{"id":"https://openalex.org/I29607241","display_name":"\u00c9cole Normale Sup\u00e9rieure - PSL","ror":"https://ror.org/05a0dhs15","country_code":"FR","type":"other","lineage":["https://openalex.org/I2746051580","https://openalex.org/I29607241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Oleksandr Zinenko","raw_affiliation_strings":["Inria and ENS, Paris, France"],"affiliations":[{"raw_affiliation_string":"Inria and ENS, Paris, France","institution_ids":["https://openalex.org/I29607241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023299580","display_name":"Theodoros Theodoridis","orcid":"https://orcid.org/0000-0002-0896-9997"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Theodoros Theodoridis","raw_affiliation_strings":["ETH Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035445731","display_name":"Priya Goyal","orcid":"https://orcid.org/0009-0009-3125-9123"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priya Goyal","raw_affiliation_strings":["Facebook AI Research, New York City, NY, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, New York City, NY, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008830900","display_name":"Zachary DeVito","orcid":"https://orcid.org/0009-0002-8863-1503"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Devito","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071127035","display_name":"William S. Moses","orcid":"https://orcid.org/0000-0003-2627-0642"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William S. Moses","raw_affiliation_strings":["MIT CSAIL, Cambridge, MA, USA","Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL, Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112473999","display_name":"Sven Verdoolaege","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sven Verdoolaege","raw_affiliation_strings":["Polly Labs 8 Facebook AI Research, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Polly Labs 8 Facebook AI Research, Leuven, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082293572","display_name":"Andrew Adams","orcid":"https://orcid.org/0000-0001-8925-9956"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Adams","raw_affiliation_strings":["Facebook AI Research, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063162788","display_name":"Albert Cohen","orcid":"https://orcid.org/0000-0002-8866-5343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albert Cohen","raw_affiliation_strings":["Inria, ENS and Facebook AI Research, Paris, France"],"affiliations":[{"raw_affiliation_string":"Inria, ENS and Facebook AI Research, Paris, France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5017292577"],"corresponding_institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":6.9123,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97645868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9848999977111816,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9817000031471252,"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/computer-science","display_name":"Computer science","score":0.8673202395439148},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.639320969581604},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5755425691604614},{"id":"https://openalex.org/keywords/tensor-algebra","display_name":"Tensor algebra","score":0.5497029423713684},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.532828688621521},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5146044492721558},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4241841435432434},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.42015111446380615},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4114798903465271},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3713623881340027},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3596118688583374},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34618720412254333},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.337876558303833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31326383352279663},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23261728882789612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673202395439148},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.639320969581604},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5755425691604614},{"id":"https://openalex.org/C1680195","wikidata":"https://www.wikidata.org/wiki/Q2296021","display_name":"Tensor algebra","level":5,"score":0.5497029423713684},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.532828688621521},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5146044492721558},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4241841435432434},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.42015111446380615},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4114798903465271},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3713623881340027},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3596118688583374},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34618720412254333},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.337876558303833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31326383352279663},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23261728882789612},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C100376341","wikidata":"https://www.wikidata.org/wiki/Q649977","display_name":"Jordan algebra","level":4,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.0},{"id":"https://openalex.org/C81999800","wikidata":"https://www.wikidata.org/wiki/Q1454725","display_name":"Current algebra","level":3,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3355606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355606","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355606","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02458550v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02458550","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization, 2019, 16 (4), pp.1-26. ⟨10.1145/3355606⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1145/3355606","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3355606","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3355606","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G778160037","display_name":"Computation-in-memory architecture based on resistive devices","funder_award_id":"780215","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321652","display_name":"Eidgen\u00f6ssische Technische Hochschule Z\u00fcrich","ror":"https://ror.org/05a28rw58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2979365412.pdf","grobid_xml":"https://content.openalex.org/works/W2979365412.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W93506392","https://openalex.org/W103531544","https://openalex.org/W288065879","https://openalex.org/W424435301","https://openalex.org/W1489951562","https://openalex.org/W1494930385","https://openalex.org/W1538021842","https://openalex.org/W1552268159","https://openalex.org/W1558370006","https://openalex.org/W1598202309","https://openalex.org/W1789336918","https://openalex.org/W1978400480","https://openalex.org/W1991009705","https://openalex.org/W1995270665","https://openalex.org/W2005368204","https://openalex.org/W2006312753","https://openalex.org/W2034761517","https://openalex.org/W2051305716","https://openalex.org/W2055312318","https://openalex.org/W2060221201","https://openalex.org/W2071110673","https://openalex.org/W2072373931","https://openalex.org/W2077143534","https://openalex.org/W2083056254","https://openalex.org/W2084917734","https://openalex.org/W2096070062","https://openalex.org/W2102976251","https://openalex.org/W2135653967","https://openalex.org/W2141280299","https://openalex.org/W2154579312","https://openalex.org/W2157099283","https://openalex.org/W2163491234","https://openalex.org/W2165706001","https://openalex.org/W2168519934","https://openalex.org/W2169492033","https://openalex.org/W2186615578","https://openalex.org/W2291192259","https://openalex.org/W2294854295","https://openalex.org/W2295739661","https://openalex.org/W2296218291","https://openalex.org/W2318529993","https://openalex.org/W2384495648","https://openalex.org/W2412412865","https://openalex.org/W2471164860","https://openalex.org/W2556804450","https://openalex.org/W2561675875","https://openalex.org/W2590246587","https://openalex.org/W2604292070","https://openalex.org/W2606722458","https://openalex.org/W2620263509","https://openalex.org/W2622263826","https://openalex.org/W2724694202","https://openalex.org/W2766362889","https://openalex.org/W2788464413","https://openalex.org/W2798341898","https://openalex.org/W2804500013","https://openalex.org/W2806891462","https://openalex.org/W2899771611","https://openalex.org/W2901494728","https://openalex.org/W2942460556","https://openalex.org/W2949251082","https://openalex.org/W2953212265","https://openalex.org/W2953328958","https://openalex.org/W2953384591","https://openalex.org/W2983923412","https://openalex.org/W3023540311","https://openalex.org/W3113163436","https://openalex.org/W3203568064","https://openalex.org/W4213041029","https://openalex.org/W4231316372","https://openalex.org/W4248073216","https://openalex.org/W4250004408","https://openalex.org/W4252411141","https://openalex.org/W4285719527","https://openalex.org/W6904045323","https://openalex.org/W6959619739"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W3169240678","https://openalex.org/W4381050447"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"frameworks":[2],"automate":[3],"the":[4,32,55,78,90,107,118,138],"deployment,":[5],"distribution,":[6],"synchronization,":[7],"memory":[8],"allocation,":[9],"and":[10,51,66,98,115,135],"hardware":[11],"acceleration":[12],"of":[13,18,57,80,110,122],"models":[14],"represented":[15],"as":[16,27],"graphs":[17],"computational":[19],"operators.":[20],"These":[21],"operators":[22,42],"wrap":[23],"high-performance":[24,103,123],"libraries":[25],"such":[26],"cuDNN":[28],"or":[29],"NNPACK.":[30],"When":[31],"computation":[33],"does":[34],"not":[35],"match":[36],"any":[37],"predefined":[38],"library":[39],"call,":[40],"custom":[41],"must":[43],"be":[44],"implemented,":[45],"often":[46,136],"at":[47],"high":[48],"engineering":[49],"cost":[50],"performance":[52,131,139],"penalty,":[53],"limiting":[54],"pace":[56],"innovation.":[58],"To":[59],"address":[60],"this":[61],"productivity":[62],"gap,":[63],"we":[64],"propose":[65],"evaluate:":[67],"(1)":[68],"a":[69,73,84],"domain-specific":[70],"language":[71],"with":[72],"tensor":[74,128],"notation":[75],"close":[76],"to":[77,101],"mathematics":[79],"deep":[81],"learning;":[82],"(2)":[83],"Just-In-Time":[85],"optimizing":[86],"compiler":[87],"based":[88],"on":[89],"polyhedral":[91],"framework;":[92],"(3)":[93],"carefully":[94],"coordinated":[95],"linear":[96],"optimization":[97],"evolutionary":[99],"algorithms":[100],"synthesize":[102],"CUDA":[104],"kernels;":[105],"(4)":[106],"transparent":[108],"integration":[109],"our":[111],"flow":[112],"into":[113],"PyTorch":[114],"Caffe2,":[116],"providing":[117],"fully":[119],"automatic":[120],"synthesis":[121],"GPU":[124],"kernels":[125],"from":[126],"simple":[127],"algebra.":[129],"The":[130],"is":[132],"comparable":[133],"to,":[134],"exceeds":[137],"of,":[140],"highly":[141],"tuned":[142],"libraries.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":7}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}