{"id":"https://openalex.org/W3008102594","doi":"https://doi.org/10.1145/3368826.3377912","title":"Automatic generation of high-performance quantized machine learning kernels","display_name":"Automatic generation of high-performance quantized machine learning kernels","publication_year":2020,"publication_date":"2020-02-21","ids":{"openalex":"https://openalex.org/W3008102594","doi":"https://doi.org/10.1145/3368826.3377912","mag":"3008102594"},"language":"en","primary_location":{"id":"doi:10.1145/3368826.3377912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368826.3377912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368826.3377912","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3368826.3377912","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044149951","display_name":"Meghan Cowan","orcid":"https://orcid.org/0000-0002-1052-0179"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meghan Cowan","raw_affiliation_strings":["University of Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103206590","display_name":"Thierry Moreau","orcid":"https://orcid.org/0000-0002-5257-4044"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thierry Moreau","raw_affiliation_strings":["University of Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471083","display_name":"Tianqi Chen","orcid":"https://orcid.org/0000-0002-2336-1875"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianqi Chen","raw_affiliation_strings":["University of Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055964348","display_name":"James Bornholt","orcid":"https://orcid.org/0000-0002-3258-3226"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Bornholt","raw_affiliation_strings":["University of Texas at Austin, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081914923","display_name":"Lu\u00eds Ceze","orcid":"https://orcid.org/0000-0002-1377-6217"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Ceze","raw_affiliation_strings":["University of Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"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":true,"cited_by_count":43,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9970999956130981,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9957000017166138,"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/exploit","display_name":"Exploit","score":0.9040235877037048},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.8214403390884399},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.8043519258499146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019272089004517},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6776752471923828},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5744749903678894},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5550254583358765},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5414227843284607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40288230776786804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39353659749031067},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2666822671890259},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14657267928123474},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07235503196716309}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.9040235877037048},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.8214403390884399},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8043519258499146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019272089004517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6776752471923828},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5744749903678894},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5550254583358765},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5414227843284607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40288230776786804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39353659749031067},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2666822671890259},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14657267928123474},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07235503196716309},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368826.3377912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368826.3377912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368826.3377912","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3368826.3377912","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368826.3377912","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368826.3377912","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1619329254","display_name":"SHF: Large: General-Purpose Approximate Computing Across the System Stack","funder_award_id":"1518703","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8924760687","display_name":null,"funder_award_id":"CCF-1518703","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3008102594.pdf","grobid_xml":"https://content.openalex.org/works/W3008102594.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2048266589","https://openalex.org/W2055312318","https://openalex.org/W2057156093","https://openalex.org/W2110848488","https://openalex.org/W2117539524","https://openalex.org/W2136952590","https://openalex.org/W2149236697","https://openalex.org/W2162960800","https://openalex.org/W2163605009","https://openalex.org/W2163671349","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2294286398","https://openalex.org/W2319920447","https://openalex.org/W2325939864","https://openalex.org/W2563587242","https://openalex.org/W2565125333","https://openalex.org/W2586654419","https://openalex.org/W2606722458","https://openalex.org/W2761953162","https://openalex.org/W2766205627","https://openalex.org/W2798956872","https://openalex.org/W2810704618","https://openalex.org/W2886991855","https://openalex.org/W2953212265","https://openalex.org/W2953384591","https://openalex.org/W2963114857","https://openalex.org/W2963122961","https://openalex.org/W2963405501","https://openalex.org/W2963960923","https://openalex.org/W3102169921","https://openalex.org/W4238194115","https://openalex.org/W4242364663"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146"],"abstract_inverted_index":{"Quantization":[0],"optimizes":[1],"machine":[2],"learning":[3],"inference":[4],"for":[5,56],"resource":[6],"constrained":[7],"environments":[8],"by":[9],"reducing":[10],"the":[11,17],"precision":[12],"of":[13],"its":[14],"computation.":[15],"In":[16],"extreme,":[18],"even":[19],"single-bit":[20],"computations":[21],"can":[22],"produce":[23],"acceptable":[24],"results":[25],"at":[26],"dramatically":[27],"lower":[28],"cost.":[29],"But":[30],"this":[31],"ultra-low-precision":[32],"quantization":[33],"is":[34],"difficult":[35],"to":[36,68,70],"exploit":[37],"because":[38],"extracting":[39],"optimal":[40],"performance":[41],"requires":[42],"hand-tuning":[43],"both":[44],"high-level":[45],"scheduling":[46],"decisions":[47],"and":[48,64],"low-level":[49],"implementations.":[50],"As":[51],"a":[52,57],"result,":[53],"practitioners":[54],"settle":[55],"few":[58],"predefined":[59],"quantized":[60],"kernels,":[61],"sacrificing":[62],"optimality":[63],"restricting":[65],"their":[66],"ability":[67],"adapt":[69],"new":[71],"hardware.":[72]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}