{"id":"https://openalex.org/W4404331863","doi":"https://doi.org/10.1145/3701996","title":"ATP: Achieving Throughput Peak for DNN Training via Smart GPU Memory Management","display_name":"ATP: Achieving Throughput Peak for DNN Training via Smart GPU Memory Management","publication_year":2024,"publication_date":"2024-11-13","ids":{"openalex":"https://openalex.org/W4404331863","doi":"https://doi.org/10.1145/3701996"},"language":"en","primary_location":{"id":"doi:10.1145/3701996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701996","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701996","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090150274","display_name":"Weiduo Chen","orcid":"https://orcid.org/0000-0001-5284-959X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiduo Chen","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-5284-959X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332436","display_name":"Xiaoshe Dong","orcid":"https://orcid.org/0000-0002-9003-2625"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshe Dong","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-9003-2625","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102406437","display_name":"Fan Zhang","orcid":"https://orcid.org/0009-0009-0887-3328"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0009-0887-3328","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103185885","display_name":"Bowen Li","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Li","raw_affiliation_strings":["School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0003-8630-2324","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374813","display_name":"Yufei Wang","orcid":"https://orcid.org/0000-0001-6403-4259"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Wang","raw_affiliation_strings":["Information and Telecommunications Branch, State Grid Shaanxi Electric Power Company, Xi\u2019an, China","Information and Telecommunications Branch, State Grid Shaanxi Electric Power Company, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-6403-4259","affiliations":[{"raw_affiliation_string":"Information and Telecommunications Branch, State Grid Shaanxi Electric Power Company, Xi\u2019an, China","institution_ids":["https://openalex.org/I17442442"]},{"raw_affiliation_string":"Information and Telecommunications Branch, State Grid Shaanxi Electric Power Company, Xi'an, China","institution_ids":["https://openalex.org/I17442442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109103720","display_name":"Qiang Wang","orcid":"https://orcid.org/0000-0001-9179-6611"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["Xi\u2019an Jiaotong University, Xi\u2019an, China","Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-9179-6611","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University, Xi\u2019an, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090150274"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5432251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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":0.9976999759674072,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7988411784172058},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7596914768218994},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6703965067863464},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4310164749622345},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.342136949300766},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32831889390945435},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2030491828918457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988411784172058},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7596914768218994},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6703965067863464},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4310164749622345},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.342136949300766},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32831889390945435},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2030491828918457},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701996","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3701996","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701996","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701996","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404331863.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W2002555321","https://openalex.org/W2064675550","https://openalex.org/W2087866311","https://openalex.org/W2108598243","https://openalex.org/W2155893237","https://openalex.org/W2302255633","https://openalex.org/W2489529491","https://openalex.org/W2562374379","https://openalex.org/W2766839578","https://openalex.org/W2912759934","https://openalex.org/W2988916019","https://openalex.org/W3006050796","https://openalex.org/W3012479151","https://openalex.org/W3012514909","https://openalex.org/W3015098801","https://openalex.org/W3153309660","https://openalex.org/W3197217317","https://openalex.org/W4226418754","https://openalex.org/W4245602507","https://openalex.org/W4285148475","https://openalex.org/W4301361180","https://openalex.org/W4301871280","https://openalex.org/W4312053794","https://openalex.org/W4313066878","https://openalex.org/W4320729330","https://openalex.org/W4376455467","https://openalex.org/W6703652217"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Due":[0],"to":[1,57,74,113,132,164],"the":[2,6,15,23,36,76,88,99,124,158],"limited":[3],"GPU":[4,26,51,63,102,159],"memory,":[5],"performance":[7,60,79,128],"of":[8,25,38,139],"large":[9,140],"DNNs":[10],"training":[11,59,83,127,156],"is":[12],"constrained":[13],"by":[14,61,81,162],"unscalable":[16],"batch":[17],"size.":[18],"Existing":[19],"studies":[20],"partially":[21],"address":[22],"issue":[24],"memory":[27,52,64,90,103,160],"limit":[28,161],"through":[29],"tensor":[30],"recomputation":[31,47,94,119],"and":[32,48,71,86,95,105,120],"swapping,":[33,121],"but":[34],"overlook":[35],"exploration":[37],"optimal":[39],"performance.":[40],"In":[41],"response,":[42],"we":[43,72],"propose":[44,73],"ATP,":[45],"a":[46,68],"swapping":[49],"based":[50],"management":[53],"framework":[54],"that":[55,144],"aims":[56],"maximize":[58],"breaking":[62],"constraints.":[65],"ATP":[66,130,145],"utilizes":[67],"throughput":[69,147],"model":[70,155],"evaluate":[75],"theoretical":[77,133],"peak":[78],"achievable":[80],"DNN":[82,126,141],"on":[84,129],"GPU,":[85],"provide":[87],"optimum":[89],"size":[91],"required":[92],"for":[93,101,115],"swapping.":[96],"We":[97],"optimize":[98],"mechanisms":[100],"pool":[104],"CUDA":[106],"stream":[107],"control,":[108],"employ":[109],"an":[110],"optimization":[111],"method":[112],"search":[114],"specific":[116],"tensors":[117],"requiring":[118],"thereby":[122],"bringing":[123],"actual":[125],"closer":[131],"values.":[134],"Evaluations":[135],"with":[136],"different":[137],"types":[138],"models":[142],"indicate":[143],"achieve":[146],"improvements":[148],"ranging":[149],"from":[150],"1.14\u223c":[151],"1.49\u00d7,":[152],"while":[153],"support":[154],"exceeding":[157],"up":[163],"9.2\u00d7.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}