{"id":"https://openalex.org/W2617189289","doi":"https://doi.org/10.1145/3079079.3079081","title":"Compile-time optimized and statically scheduled N-D convnet primitives for multi-core and many-core (Xeon Phi) CPUs","display_name":"Compile-time optimized and statically scheduled N-D convnet primitives for multi-core and many-core (Xeon Phi) CPUs","publication_year":2017,"publication_date":"2017-05-31","ids":{"openalex":"https://openalex.org/W2617189289","doi":"https://doi.org/10.1145/3079079.3079081","mag":"2617189289"},"language":"en","primary_location":{"id":"doi:10.1145/3079079.3079081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079079.3079081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5029097412","display_name":"Aleksandar Zlateski","orcid":"https://orcid.org/0000-0003-0261-1967"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"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":"Aleksandar Zlateski","raw_affiliation_strings":["Massachusetts Institute of Technology and Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology and Princeton University","institution_ids":["https://openalex.org/I20089843","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044273339","display_name":"H. Sebastian Seung","orcid":"https://orcid.org/0000-0002-8591-6733"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H Sebastian Seung","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"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":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9046999216079712},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8333684206008911},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.7173745632171631},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6921747922897339},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5281041860580444},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4920749068260193},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.4896166920661926},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.4736548662185669},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4406401515007019},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17535099387168884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9046999216079712},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8333684206008911},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.7173745632171631},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6921747922897339},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5281041860580444},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4920749068260193},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.4896166920661926},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.4736548662185669},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4406401515007019},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17535099387168884}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3079079.3079081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079079.3079081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1493004075","https://openalex.org/W1522734439","https://openalex.org/W1530262073","https://openalex.org/W1536852470","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1884620995","https://openalex.org/W1889898024","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W1983364832","https://openalex.org/W1985462363","https://openalex.org/W2040062623","https://openalex.org/W2056784365","https://openalex.org/W2096070062","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2172654076","https://openalex.org/W2211722331","https://openalex.org/W2485412435","https://openalex.org/W2487190711","https://openalex.org/W2549412286","https://openalex.org/W2561801540","https://openalex.org/W2618530766","https://openalex.org/W2738552833","https://openalex.org/W2746871167","https://openalex.org/W2963340555","https://openalex.org/W2963542991"],"related_works":["https://openalex.org/W2505067803","https://openalex.org/W4315697128","https://openalex.org/W1634740951","https://openalex.org/W2542593149","https://openalex.org/W2148563915","https://openalex.org/W2286735113","https://openalex.org/W1974923383","https://openalex.org/W3102845713","https://openalex.org/W2256091520","https://openalex.org/W2022666014"],"abstract_inverted_index":{"Convolutional":[0],"networks":[1],"(ConvNets),":[2],"largely":[3],"running":[4],"on":[5,75,192],"GPUs,":[6,25],"have":[7],"become":[8],"the":[9,21,76,83,90,101,112,130,152,201,227,235,242,245],"most":[10],"popular":[11],"approach":[12,71],"to":[13,48,73,78,107,136,205,226],"computer":[14],"vision.":[15],"Now":[16],"that":[17,89,124,176],"CPUs":[18],"are":[19,29,119],"closing":[20],"FLOPS":[22,183,243],"gap":[23],"with":[24,200],"efficient":[26],"CPU":[27,60,203,236],"algorithms":[28],"becoming":[30],"more":[31],"important.":[32],"We":[33,87,128,174],"propose":[34],"a":[35,115],"novel":[36,143],"parallel":[37,187],"and":[38,59,170,212,231],"vectorized":[39],"algorithm":[40,99,131,147,188,197],"for":[41,85,114,208,216],"N-D":[42],"convolutional":[43],"layers.":[44],"Our":[45,70,97,142,196],"goal":[46],"is":[47,72,93,148,198,237],"achieve":[49],"high":[50],"utilization":[51,191],"of":[52,56,66,150,159,162,240,244],"available":[53,182],"FLOPS,":[54],"independent":[55],"ConvNet":[57,163],"architecture":[58,92],"properties":[61],"(e.g.":[62],"vector":[63],"units,":[64],"number":[65,158],"cores,":[67,160],"cache":[68,126],"sizes).":[69],"rely":[74],"compiler":[77,113],"optimize":[79],"code,":[80],"thereby":[81],"removing":[82],"need":[84],"hand-tuning.":[86],"assume":[88],"network":[91],"known":[94],"at":[95],"compile-time.":[96],"serial":[98,178],"divides":[100],"computation":[102,153],"into":[103],"small":[104],"sub-tasks":[105],"designed":[106],"be":[108,137],"easily":[109],"optimized":[110],"by":[111,132,139],"specific":[116],"CPU.":[117],"Sub-tasks":[118],"executed":[120,138],"in":[121],"an":[122,156],"order":[123],"maximizes":[125],"reuse.":[127],"parallelize":[129],"statically":[133],"scheduling":[134,146],"tasks":[135],"each":[140],"core.":[141],"compile-time":[144],"recursive":[145],"capable":[149,239],"dividing":[151],"evenly":[154],"between":[155],"arbitrary":[157],"regardless":[161],"architecture.":[164],"It":[165],"introduces":[166],"zero":[167],"runtime":[168],"overhead":[169],"minimal":[171],"synchronization":[172],"overhead.":[173],"demonstrate":[175,223],"our":[177,186],"primitives":[179],"efficiently":[180],"utilize":[181],"(75--95%),":[184],"while":[185],"attains":[189],"50--90%":[190],"64+":[193],"core":[194],"machines.":[195],"competitive":[199],"fastest":[202],"implementation":[204],"date":[206],"(MKL2017)":[207],"2D":[209],"object":[210],"recognition,":[211],"performs":[213],"much":[214],"better":[215],"image":[217],"segmentation.":[218],"For":[219],"3D":[220],"ConvNets":[221],"we":[222],"comparable":[224],"performance":[225],"latest":[228],"GPU":[229],"hardware":[230],"software":[232],"even":[233],"though":[234],"only":[238],"half":[241],"GPU.":[246]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}