{"id":"https://openalex.org/W4391986270","doi":"https://doi.org/10.1145/3640537.3641566","title":"YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs","display_name":"YFlows: Systematic Dataflow Exploration and Code Generation for Efficient Neural Network Inference using SIMD Architectures on CPUs","publication_year":2024,"publication_date":"2024-02-17","ids":{"openalex":"https://openalex.org/W4391986270","doi":"https://doi.org/10.1145/3640537.3641566"},"language":"en","primary_location":{"id":"doi:10.1145/3640537.3641566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640537.3641566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640537.3641566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGPLAN International Conference on Compiler Construction","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/10.1145/3640537.3641566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033393090","display_name":"Cyrus Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cyrus Zhou","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0001-8768-0659","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092998402","display_name":"Zack Hassman","orcid":"https://orcid.org/0009-0007-3392-9296"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zack Hassman","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0007-3392-9296","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045033573","display_name":"Dhirpal Shah","orcid":"https://orcid.org/0009-0009-8436-8796"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhirpal Shah","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0009-8436-8796","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103140730","display_name":"Vaughn Richard","orcid":"https://orcid.org/0009-0003-1048-9532"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaughn Richard","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0009-0003-1048-9532","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101989053","display_name":"Yanjing Li","orcid":"https://orcid.org/0000-0003-0124-0463"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanjing Li","raw_affiliation_strings":["University of Chicago, Chicago, USA"],"raw_orcid":"https://orcid.org/0000-0003-0124-0463","affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9909999966621399,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9782999753952026,"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/dataflow","display_name":"Dataflow","score":0.9027512073516846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8668264150619507},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8183943033218384},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7517001628875732},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7075408697128296},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6458703875541687},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5740986466407776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5710775852203369},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5406391620635986},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4571724534034729},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.43529731035232544},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4199311137199402},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41091257333755493},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3584896922111511},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.29757755994796753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27628666162490845},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2182803750038147},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.10653117299079895}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9027512073516846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8668264150619507},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8183943033218384},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7517001628875732},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7075408697128296},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6458703875541687},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5740986466407776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5710775852203369},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5406391620635986},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4571724534034729},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43529731035232544},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4199311137199402},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41091257333755493},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3584896922111511},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.29757755994796753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27628666162490845},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2182803750038147},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.10653117299079895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":2,"locations":[{"id":"doi:10.1145/3640537.3641566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640537.3641566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640537.3641566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},{"id":"pmh:oai:uchicago.tind.io:11118","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/11118","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/11118","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3640537.3641566","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640537.3641566","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3640537.3641566","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310134","display_name":"Brandeis University","ror":"https://ror.org/05abbep66"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391986270.pdf","grobid_xml":"https://content.openalex.org/works/W4391986270.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W1982733412","https://openalex.org/W2111394443","https://openalex.org/W2114332109","https://openalex.org/W2152839228","https://openalex.org/W2322411027","https://openalex.org/W2360674415","https://openalex.org/W2416799949","https://openalex.org/W2489529491","https://openalex.org/W2604319603","https://openalex.org/W2626712922","https://openalex.org/W2809121165","https://openalex.org/W2886991855","https://openalex.org/W2911923789","https://openalex.org/W2912616132","https://openalex.org/W2913208203","https://openalex.org/W2914479353","https://openalex.org/W2914895134","https://openalex.org/W2919636550","https://openalex.org/W2950656546","https://openalex.org/W2963125010","https://openalex.org/W2966258469","https://openalex.org/W2976670629","https://openalex.org/W3004702456","https://openalex.org/W3006050796","https://openalex.org/W3008102594","https://openalex.org/W3008374555","https://openalex.org/W3008769740","https://openalex.org/W3009833179","https://openalex.org/W3016220765","https://openalex.org/W3038827379","https://openalex.org/W3095092693","https://openalex.org/W3098873988","https://openalex.org/W3125750521","https://openalex.org/W3154028478","https://openalex.org/W3197326126","https://openalex.org/W3202028501","https://openalex.org/W3211787299","https://openalex.org/W4206174637","https://openalex.org/W4206634569","https://openalex.org/W4224310326","https://openalex.org/W4224903119","https://openalex.org/W4229784135","https://openalex.org/W4230315356","https://openalex.org/W4234552385","https://openalex.org/W4239088979","https://openalex.org/W4243739713","https://openalex.org/W4244713288","https://openalex.org/W4245873525","https://openalex.org/W4249932213","https://openalex.org/W4250518453","https://openalex.org/W4255823021","https://openalex.org/W4285074441","https://openalex.org/W4287748555","https://openalex.org/W4287864584","https://openalex.org/W4288083528","https://openalex.org/W4289583705","https://openalex.org/W4289656095","https://openalex.org/W4293102204","https://openalex.org/W4293102247","https://openalex.org/W4297803378","https://openalex.org/W4316252387","https://openalex.org/W4321446149","https://openalex.org/W4360897687","https://openalex.org/W4366957282","https://openalex.org/W6797854001"],"related_works":["https://openalex.org/W2187181201","https://openalex.org/W2099629705","https://openalex.org/W2963831937","https://openalex.org/W47034296","https://openalex.org/W1496703677","https://openalex.org/W2748614007","https://openalex.org/W2080419754","https://openalex.org/W2160476201","https://openalex.org/W2300162960","https://openalex.org/W1587248296"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,28,71,89,119],"challenges":[3],"associated":[4],"with":[5,11],"deploying":[6],"neural":[7,35,64,106,115,123],"networks":[8,124],"on":[9,15],"CPUs,":[10],"a":[12,34,46,93],"particular":[13],"focus":[14],"minimizing":[16],"inference":[17,97],"time":[18],"while":[19,79],"maintaining":[20],"accuracy.":[21],"Our":[22,67],"novel":[23],"approach":[24],"is":[25],"to":[26,37,61,101,110],"use":[27],"dataflow":[29,72],"(i.e.,":[30],"computation":[31],"order)":[32],"of":[33,53,96,122],"network":[36,65],"explore":[38],"data":[39],"reuse":[40,86],"opportunities":[41],"using":[42],"heuristic-guided":[43],"analysis":[44],"and":[45,84,108],"code":[47],"generation":[48],"framework,":[49],"which":[50],"enables":[51],"exploration":[52],"various":[54],"Single":[55],"Instruction,":[56],"Multiple":[57],"Data":[58],"(SIMD)":[59],"implementations":[60,121],"achieve":[62],"optimized":[63,120],"execution.":[66],"results":[68],"demonstrate":[69],"that":[70,73],"keeps":[74],"outputs":[75],"in":[76],"SIMD":[77],"registers":[78],"also":[80],"maximizing":[81],"both":[82],"input":[83],"weight":[85],"consistently":[87],"yields":[88],"best":[90],"performance":[91],"for":[92,104,113],"wide":[94],"variety":[95],"workloads,":[98],"achieving":[99],"up":[100,109],"3x":[102],"speedup":[103,112],"8-bit":[105],"networks,":[107,116],"4.8x":[111],"binary":[114],"respectively,":[117],"over":[118],"today.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}