{"id":"https://openalex.org/W4282959697","doi":"https://doi.org/10.1145/3498361.3538940","title":"mGEMM","display_name":"mGEMM","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4282959697","doi":"https://doi.org/10.1145/3498361.3538940"},"language":"en","primary_location":{"id":"doi:10.1145/3498361.3538940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3498361.3538940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},"type":"article","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/A5114348419","display_name":"Jongseok Park","orcid":"https://orcid.org/0009-0001-5397-8112"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongseok Park","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086533844","display_name":"Kyungmin Bin","orcid":"https://orcid.org/0000-0001-5643-6688"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungmin Bin","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020806825","display_name":"Kyunghan Lee","orcid":"https://orcid.org/0000-0001-8647-1476"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyunghan Lee","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4215,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82488563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9955999851226807,"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":0.839748203754425},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7198687195777893},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.536824643611908},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49425554275512695},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4938550591468811},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.42691460251808167},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4242761731147766},{"id":"https://openalex.org/keywords/block-size","display_name":"Block size","score":0.42364081740379333},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4196268320083618},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4145865738391876},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3567396402359009},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2780902087688446},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2516610026359558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1227981448173523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839748203754425},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7198687195777893},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.536824643611908},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49425554275512695},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4938550591468811},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42691460251808167},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4242761731147766},{"id":"https://openalex.org/C41431624","wikidata":"https://www.wikidata.org/wiki/Q1053357","display_name":"Block size","level":3,"score":0.42364081740379333},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4196268320083618},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4145865738391876},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3567396402359009},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2780902087688446},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2516610026359558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1227981448173523},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3498361.3538940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3498361.3538940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services","raw_type":"proceedings-article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/185317","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/185317","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2043275593","https://openalex.org/W3008010570","https://openalex.org/W3165698711","https://openalex.org/W6600120041","https://openalex.org/W6600424091","https://openalex.org/W6600655691","https://openalex.org/W6601426737","https://openalex.org/W6603394118","https://openalex.org/W6603994023","https://openalex.org/W6608099265","https://openalex.org/W6629448196","https://openalex.org/W6630431485","https://openalex.org/W6819060087","https://openalex.org/W6824208151"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W3157543420","https://openalex.org/W2360814058"],"abstract_inverted_index":{"The":[0],"convolution":[1,18,71,121,147,162,217],"layer":[2],"is":[3],"the":[4,17,40,70,97,110,125,134,146,153,161,184,188,221],"key":[5],"building":[6],"block":[7],"in":[8,37,77,130,138,159,187,213,224,227],"many":[9],"neural":[10,175],"network":[11],"designs.":[12],"Most":[13],"high-performance":[14],"implementations":[15],"of":[16,61,88,96,104,113,136,190],"operation":[19,72,148,163],"rely":[20],"on":[21,46],"GEMM":[22,137,167],"(General":[23],"Matrix":[24],"Multiplication)":[25],"to":[26,73,94,164,208,220],"achieve":[27],"high":[28],"computational":[29],"throughput":[30],"with":[31],"a":[32,50,120,140,165,199],"large":[33,86],"workload":[34],"size.":[35,55],"However,":[36],"mobile":[38],"environments,":[39],"user":[41],"experience":[42],"priority":[43],"puts":[44],"focus":[45],"low-latency":[47],"inferences":[48],"over":[49,173],"single":[51],"or":[52],"limited":[53],"batch":[54],"This":[56],"signifies":[57],"two":[58],"major":[59],"problems":[60],"current":[62,105],"GEMM-based":[63,66,83,106],"solutions:":[64],"1)":[65],"solutions":[67,84,186],"require":[68],"mapping":[69],"GEMM,":[74],"causing":[75],"overheads":[76],"both":[78],"computation":[79],"and":[80,116,177,194,210,216],"memory,":[81],"2)":[82],"lose":[85],"opportunities":[87],"data":[89],"reuse":[90],"while":[91,152,230],"mapping,":[92],"leading":[93],"under-utilization":[95],"given":[98],"hardware.":[99],"Through":[100],"an":[101],"in-depth":[102],"analysis":[103],"solutions,":[107],"we":[108,117],"identify":[109],"root":[111],"cause":[112],"these":[114],"problems,":[115,127],"propose":[118],"mGEMM,":[119],"solution":[122],"that":[123,142,181],"overcomes":[124],"aforementioned":[126],"without":[128,149],"changes":[129],"accuracy.":[131],"mGEMM":[132,182,205],"expands":[133],"structure":[135],"such":[139],"way":[141],"it":[143],"can":[144],"accommodate":[145],"any":[150],"overhead,":[151,193],"existing":[154,185],"algorithms":[155],"suffer":[156],"from":[157],"inefficiencies":[158],"converting":[160],"static":[166],"algorithm.":[168],"Our":[169],"extensive":[170],"evaluations":[171],"done":[172],"various":[174],"networks":[176],"test":[178],"devices":[179],"show":[180],"outperforms":[183],"aspects":[189],"latency,":[191],"memory":[192],"energy":[195,228],"consumption.":[196],"In":[197],"running":[198],"real-world":[200],"application,":[201],"YoloV3-Tiny":[202],"object":[203],"detection,":[204],"achieves":[206],"up":[207],"1.29\u00d7":[209],"1.58\u00d7":[211],"speedup":[212],"total":[214],"latency":[215,218],"compared":[219],"state-of-the-art,":[222],"resulting":[223],"15.5%":[225],"reduction":[226],"consumption":[229],"using":[231],"only":[232],"near-minimum":[233],"heap":[234],"memory.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-06-17T00:00:00"}