{"id":"https://openalex.org/W4409132189","doi":"https://doi.org/10.1109/hpec62836.2024.10938425","title":"High Performance Im2win and Direct Convolutions Using Three Tensor Layouts on SIMD Architectures","display_name":"High Performance Im2win and Direct Convolutions Using Three Tensor Layouts on SIMD Architectures","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409132189","doi":"https://doi.org/10.1109/hpec62836.2024.10938425"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5100607531","display_name":"Xiang Fu","orcid":"https://orcid.org/0000-0002-1365-8501"},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Fu","raw_affiliation_strings":["Nanchang Hangkong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071724015","display_name":"Xinpeng Zhang","orcid":"https://orcid.org/0000-0001-5867-1315"},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinpeng Zhang","raw_affiliation_strings":["Nanchang Hangkong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101514631","display_name":"Jixiang Ma","orcid":"https://orcid.org/0000-0002-9649-0088"},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixiang Ma","raw_affiliation_strings":["Nanchang Hangkong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009319979","display_name":"Peng Zhao","orcid":"https://orcid.org/0000-0001-7942-388X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhao","raw_affiliation_strings":["Microsoft,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012433446","display_name":"Shuai L\u00fc","orcid":"https://orcid.org/0000-0002-8081-4498"},"institutions":[{"id":"https://openalex.org/I927504317","display_name":"Nanchang Hangkong University","ror":"https://ror.org/0369pvp92","country_code":"CN","type":"education","lineage":["https://openalex.org/I927504317"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Lu","raw_affiliation_strings":["Nanchang Hangkong University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanchang Hangkong University,China","institution_ids":["https://openalex.org/I927504317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054943576","display_name":"Tony Liu","orcid":"https://orcid.org/0000-0003-3980-9803"},"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":"Xu T. Liu","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":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35175879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9506999850273132,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9483000040054321,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/simd","display_name":"SIMD","score":0.7625466585159302},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7379156351089478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7002074122428894},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5790715217590332},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4349684417247772},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37026655673980713},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1530930995941162}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7625466585159302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7379156351089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002074122428894},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5790715217590332},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4349684417247772},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37026655673980713},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1530930995941162},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G6598054934","display_name":"OAC Core: Cost-Adaptive Monitoring and Real-Time Tuning at Function-Level","funder_award_id":"2402542","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2002257715","https://openalex.org/W2002555321","https://openalex.org/W2063249715","https://openalex.org/W2604319603","https://openalex.org/W2883780447","https://openalex.org/W2908621704","https://openalex.org/W2951810231","https://openalex.org/W2951894856","https://openalex.org/W4205546691","https://openalex.org/W4301418577","https://openalex.org/W4308090463","https://openalex.org/W4386106891","https://openalex.org/W4386896826","https://openalex.org/W4400188922","https://openalex.org/W6630903078","https://openalex.org/W6631660994","https://openalex.org/W6637151318","https://openalex.org/W6713134421","https://openalex.org/W6740373327","https://openalex.org/W6752390237","https://openalex.org/W6766978945","https://openalex.org/W6870468394"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W1587248296","https://openalex.org/W2117755361","https://openalex.org/W2286348849","https://openalex.org/W2063770303","https://openalex.org/W2018511057"],"abstract_inverted_index":{"Convolution":[0],"is":[1,11,34],"the":[2,81,86,94,104,108,126],"core":[3],"component":[4],"within":[5],"deep":[6],"neural":[7],"networks":[8],"and":[9,14,29,63,65,76,89,131,137,144],"it":[10],"computationally":[12],"intensive":[13],"time":[15],"consuming.":[16],"Tensor":[17],"data":[18,43,56],"layouts":[19,44,57,96],"significantly":[20,124],"impact":[21],"convolution":[22,49,84,88,92,106],"operations":[23],"in":[24],"terms":[25],"of":[26,38,69,128,146],"memory":[27],"access":[28],"computational":[30],"efficiency.":[31],"Yet,":[32],"there":[33],"still":[35],"a":[36,67],"lack":[37],"comprehensive":[39],"performance":[40,116,127],"characterization":[41],"on":[42,45,97],"SIMD":[46,98],"architectures":[47],"concerning":[48],"methods.":[50],"This":[51],"paper":[52],"proposes":[53],"three":[54],"novel":[55],"for":[58,73],"im2win":[59,77,83,105,130,136],"convolution:":[60],"NHWC,":[61],"CHWN,":[62],"CHWN8,":[64],"introduces":[66],"set":[68],"general":[70],"optimization":[71],"techniques":[72],"both":[74,129],"direct":[75,87,132,138],"convolutions.":[78,133],"We":[79],"compare":[80],"optimized":[82,135],"with":[85,107],"PyTorch's":[90],"im2col-based":[91],"across":[93],"aforementioned":[95],"machines.":[99],"The":[100],"experiments":[101],"demonstrated":[102],"that":[103],"new":[109],"NHWC":[110],"layout":[111],"achieved":[112,140],"up":[113,141],"to":[114,142],"355%":[115],"speedup":[117],"over":[118],"NCHW":[119],"layout.":[120],"Our":[121,134],"optimizations":[122],"also":[123],"improve":[125],"convolutions":[139],"95%":[143],"94%":[145],"machine's":[147],"theoretical":[148],"peak":[149],"performance,":[150],"respectively.":[151]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}