{"id":"https://openalex.org/W3010830594","doi":"https://doi.org/10.1145/3373376.3378465","title":"AutoTM: Automatic Tensor Movement in Heterogeneous Memory Systems using Integer Linear Programming","display_name":"AutoTM: Automatic Tensor Movement in Heterogeneous Memory Systems using Integer Linear Programming","publication_year":2020,"publication_date":"2020-03-09","ids":{"openalex":"https://openalex.org/W3010830594","doi":"https://doi.org/10.1145/3373376.3378465","mag":"3010830594"},"language":"en","primary_location":{"id":"doi:10.1145/3373376.3378465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373376.3378465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373376.3378465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3373376.3378465","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061186224","display_name":"Mark Hildebrand","orcid":"https://orcid.org/0000-0001-6105-1643"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mark Hildebrand","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630991","display_name":"Jawad Khan","orcid":"https://orcid.org/0000-0001-6911-3546"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jawad Khan","raw_affiliation_strings":["Intel Corporation, Hillsboro, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031525529","display_name":"Sanjeev Trika","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Trika","raw_affiliation_strings":["Intel Corporation, Hillsboro, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation, Hillsboro, OR, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017932233","display_name":"Jason Lowe-Power","orcid":"https://orcid.org/0000-0002-8880-8703"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Lowe-Power","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089377852","display_name":"Venkatesh Akella","orcid":"https://orcid.org/0000-0003-3014-5326"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatesh Akella","raw_affiliation_strings":["University of California, Davis, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061186224"],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":9.1966,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.98632069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"875","last_page":"890"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.993399977684021,"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":0.8102129697799683},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7608761191368103},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7298352122306824},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6891636252403259},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.544877290725708},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5150065422058105},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4802677631378174},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.45335710048675537},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4332195818424225},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4299762547016144},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.42519378662109375},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32870766520500183},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.31676769256591797},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2795358896255493},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21276187896728516},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14744988083839417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1207176148891449},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.10735702514648438},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.09443578124046326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07959938049316406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102129697799683},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7608761191368103},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7298352122306824},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6891636252403259},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.544877290725708},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5150065422058105},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4802677631378174},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.45335710048675537},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4332195818424225},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4299762547016144},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.42519378662109375},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32870766520500183},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31676769256591797},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2795358896255493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21276187896728516},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14744988083839417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1207176148891449},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.10735702514648438},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.09443578124046326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07959938049316406}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3373376.3378465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373376.3378465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373376.3378465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3373376.3378465","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3373376.3378465","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3373376.3378465","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.5099999904632568,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G8791118704","display_name":null,"funder_award_id":"CNS-1850566","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"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010830594.pdf","grobid_xml":"https://content.openalex.org/works/W3010830594.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W262467192","https://openalex.org/W1552561242","https://openalex.org/W1557855942","https://openalex.org/W1686810756","https://openalex.org/W1918816242","https://openalex.org/W1989831720","https://openalex.org/W2026247162","https://openalex.org/W2032039029","https://openalex.org/W2060171681","https://openalex.org/W2068993993","https://openalex.org/W2094605327","https://openalex.org/W2102003408","https://openalex.org/W2112796928","https://openalex.org/W2115148068","https://openalex.org/W2117130368","https://openalex.org/W2159792012","https://openalex.org/W2161963794","https://openalex.org/W2274287116","https://openalex.org/W2489529491","https://openalex.org/W2559655401","https://openalex.org/W2581624817","https://openalex.org/W2604595776","https://openalex.org/W2742513757","https://openalex.org/W2747329762","https://openalex.org/W2783292547","https://openalex.org/W2784561332","https://openalex.org/W2798337732","https://openalex.org/W2798707674","https://openalex.org/W2893749619","https://openalex.org/W2900810680","https://openalex.org/W2914554687","https://openalex.org/W2921153466","https://openalex.org/W2934584470","https://openalex.org/W2936570671","https://openalex.org/W2947737663","https://openalex.org/W2951966972","https://openalex.org/W2964024144","https://openalex.org/W2966553076","https://openalex.org/W3105558219","https://openalex.org/W3138798301","https://openalex.org/W4244275790","https://openalex.org/W6678107996","https://openalex.org/W6679436768","https://openalex.org/W6687483927","https://openalex.org/W6725739302"],"related_works":["https://openalex.org/W4293430534","https://openalex.org/W2342813629","https://openalex.org/W3150934690","https://openalex.org/W2335743642","https://openalex.org/W4297812927","https://openalex.org/W2800412005","https://openalex.org/W1976244802","https://openalex.org/W2083934844","https://openalex.org/W1992487929","https://openalex.org/W4386903460"],"abstract_inverted_index":{"Memory":[0],"capacity":[1],"is":[2,137],"a":[3,25,38,91,123,131,138,164],"key":[4],"bottleneck":[5],"for":[6,167],"training":[7],"large":[8,169],"scale":[9],"neural":[10,86],"networks.":[11,170],"Intel\u00ae":[12],"Optane#8482;":[13],"DC":[14],"PMM":[15,127],"(persistent":[16],"memory":[17,58],"modules)":[18],"which":[19,144],"are":[20,24],"available":[21],"as":[22,163],"NVDIMMs":[23],"disruptive":[26],"technology":[27,59],"that":[28],"promises":[29],"significantly":[30],"higher":[31],"read":[32],"bandwidth":[33],"than":[34,43],"traditional":[35,44],"SSDs":[36],"at":[37],"lower":[39],"cost":[40],"per":[41],"bit":[42],"DRAM.":[45],"In":[46],"this":[47,56],"work":[48],"we":[49,72],"show":[50],"how":[51],"to":[52,60,89,103,110,120],"take":[53,73],"advantage":[54,74],"of":[55,64,75,79,122,147],"new":[57],"minimize":[61],"the":[62,76,80],"amount":[63],"DRAM":[65,112,125,162],"required":[66],"without":[67],"compromising":[68],"performance":[69,159],"significantly.":[70],"Specifically,":[71],"static":[77],"nature":[78],"underlying":[81],"computational":[82],"graphs":[83],"in":[84],"deep":[85],"network":[87],"applications":[88],"develop":[90],"profile":[92],"guided":[93],"optimization":[94],"based":[95,152],"on":[96],"Integer":[97],"Linear":[98],"Programming":[99],"(ILP)":[100],"called":[101],"AutoTM":[102],"optimally":[104],"assign":[105],"and":[106],"move":[107],"live":[108],"tensors":[109],"either":[111],"or":[113],"NVDIMMs.":[114],"Our":[115],"approach":[116],"can":[117],"replace":[118],"50%":[119],"80%":[121],"system's":[124],"with":[126],"while":[128],"only":[129],"losing":[130],"geometric":[132],"mean":[133],"27.7%":[134],"performance.":[135,148],"This":[136],"significant":[139],"improvement":[140],"over":[141,160],"first-touch":[142],"NUMA,":[143],"loses":[145],"71.9%":[146],"The":[149],"proposed":[150],"ILP":[151],"synchronous":[153],"scheduling":[154],"technique":[155],"also":[156],"provides":[157],"2x":[158],"using":[161],"hardware-controlled":[165],"cache":[166],"very":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}