{"id":"https://openalex.org/W7116312421","doi":"https://doi.org/10.1145/3750720.3757284","title":"Hardware-aware Graph Partition for Mobile Inference Acceleration","display_name":"Hardware-aware Graph Partition for Mobile Inference Acceleration","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116312421","doi":"https://doi.org/10.1145/3750720.3757284"},"language":null,"primary_location":{"id":"doi:10.1145/3750720.3757284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3750720.3757284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","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/A5058163038","display_name":"Meng-Shiun Yu","orcid":"https://orcid.org/0000-0002-0471-0216"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Meng-Shiun Yu","raw_affiliation_strings":["National Tsing Hua University, Taiwan, HsinChu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-0471-0216","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan, HsinChu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120946218","display_name":"Feng-Yi Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Feng-Yi Zhan","raw_affiliation_strings":["National Tsing Hua University, Taiwan, HsinChu, Taiwan"],"raw_orcid":"https://orcid.org/0009-0008-0532-7009","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan, HsinChu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ming-Zhang Huang","orcid":"https://orcid.org/0009-0009-9643-552X"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Zhang Huang","raw_affiliation_strings":["National Tsing Hua University, Taiwan, HsinChu, Taiwan"],"raw_orcid":"https://orcid.org/0009-0009-9643-552X","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan, HsinChu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102235959","display_name":"Tai-Liang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tai-Liang Chen","raw_affiliation_strings":["National Tsing Hua University, Taiwan, HsinChu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3347-8161","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan, HsinChu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043741054","display_name":"Jenq-Kuen Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jenq-Kuen Lee","raw_affiliation_strings":["National Tsing Hua University, Taiwan, HsinChu, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9919-6258","affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Taiwan, HsinChu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058163038"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60336789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.7479000091552734,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.7479000091552734,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.06520000100135803,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.02889999933540821,"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/leverage","display_name":"Leverage (statistics)","score":0.5471000075340271},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5307000279426575},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5058000087738037},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.48420000076293945},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4683000147342682},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.46380001306533813},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.42579999566078186},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4088999927043915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5471000075340271},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5307000279426575},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5058000087738037},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.46380001306533813},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.41940000653266907},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328900009393692},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3043000102043152},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3750720.3757284","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3750720.3757284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2618530766","https://openalex.org/W2659864996","https://openalex.org/W2728444714","https://openalex.org/W2758475033","https://openalex.org/W2949650786","https://openalex.org/W2962835968","https://openalex.org/W2972486437","https://openalex.org/W2994776994","https://openalex.org/W3007677732","https://openalex.org/W3010466514","https://openalex.org/W3011280959","https://openalex.org/W3059989341","https://openalex.org/W3122687240","https://openalex.org/W3132445375","https://openalex.org/W3147954149","https://openalex.org/W3168541340","https://openalex.org/W4210338699","https://openalex.org/W4220956204","https://openalex.org/W4225270187","https://openalex.org/W4285269946","https://openalex.org/W4293261614","https://openalex.org/W4307922031","https://openalex.org/W4312729371","https://openalex.org/W4312834900","https://openalex.org/W4313442384","https://openalex.org/W4320068012","https://openalex.org/W4372271774","https://openalex.org/W4379051661","https://openalex.org/W4384155658","https://openalex.org/W4385532394","https://openalex.org/W4386131770","https://openalex.org/W4387868940","https://openalex.org/W4388581107","https://openalex.org/W4390224392","https://openalex.org/W4391164100","https://openalex.org/W4392295176","https://openalex.org/W4394670654","https://openalex.org/W4395106413","https://openalex.org/W4396680706","https://openalex.org/W4399168608","https://openalex.org/W4399282407","https://openalex.org/W4401386775","https://openalex.org/W4402349218","https://openalex.org/W4402427803"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"smartphones":[1],"integrate":[2],"various":[3],"specialized":[4],"hardware":[5,31,70],"units,":[6],"such":[7],"as":[8],"CPUs,":[9],"GPUs,":[10],"DSPs,":[11],"and":[12,71,110],"accelerators,":[13],"each":[14],"tailored":[15],"to":[16,28,56,77,93,123],"specific":[17],"computational":[18],"tasks.":[19],"Many":[20],"mobile":[21,58,99,137],"systems":[22],"provide":[23],"native":[24],"neural":[25],"network":[26],"APIs":[27],"leverage":[29],"these":[30],"units":[32],"efficiently.":[33],"However,":[34],"combining":[35],"compiler-aided":[36],"optimizations":[37],"with":[38,108],"NN":[39,113],"API":[40],"backends":[41],"can":[42],"further":[43],"enhance":[44],"performance.":[45],"This":[46],"paper":[47],"introduces":[48],"a":[49,79,89,124],"generic":[50],"approach":[51],"for":[52],"hardware-aware":[53],"graph":[54,90,96],"partitioning":[55,91],"accelerate":[57],"inference.":[59],"We":[60,101],"profile":[61],"the":[62,66,74,111],"operators":[63],"used":[64],"in":[65,130],"model":[67,134],"on":[68,83,98,136],"supported":[69],"then":[72],"use":[73,102],"profiling":[75],"data":[76],"create":[78],"cost":[80,85],"model.":[81],"Based":[82],"this":[84],"model,":[86],"we":[87],"apply":[88],"strategy":[92],"maximize":[94],"computation":[95],"performance":[97],"devices.":[100],"an":[103],"end-to-end":[104],"compilation":[105],"pipeline":[106],"built":[107],"TVM":[109],"Android":[112],"API,":[114],"experimental":[115],"results":[116],"show":[117],"that":[118],"our":[119],"method":[120],"achieves":[121],"up":[122],"17.29\u00d7":[125],"speedup,":[126],"validating":[127],"its":[128],"effectiveness":[129],"enhancing":[131],"deep":[132],"learning":[133],"execution":[135],"platforms.":[138]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}