{"id":"https://openalex.org/W4384030041","doi":"https://doi.org/10.1145/3607870","title":"SMaLL: Software for Rapidly Instantiating Machine Learning Libraries","display_name":"SMaLL: Software for Rapidly Instantiating Machine Learning Libraries","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384030041","doi":"https://doi.org/10.1145/3607870"},"language":"en","primary_location":{"id":"doi:10.1145/3607870","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607870","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://dx.doi.org/10.1145/3607870","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084840391","display_name":"Upasana Sridhar","orcid":"https://orcid.org/0000-0002-2416-3651"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Upasana Sridhar","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-2416-3651","affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070137887","display_name":"Nicholai Tukanov","orcid":"https://orcid.org/0009-0006-0421-4462"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholai Tukanov","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0006-0421-4462","affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015932389","display_name":"Elliott Binder","orcid":"https://orcid.org/0000-0003-3588-5606"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliott Binder","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-3588-5606","affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019607600","display_name":"Tze Meng Low","orcid":"https://orcid.org/0000-0002-5179-8249"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tze Meng Low","raw_affiliation_strings":["ECE, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-5179-8249","affiliations":[{"raw_affiliation_string":"ECE, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028007059","display_name":"Scott McMillan","orcid":"https://orcid.org/0000-0003-1868-5178"},"institutions":[{"id":"https://openalex.org/I114772536","display_name":"Software Engineering Institute","ror":"https://ror.org/01xqjjn94","country_code":"US","type":"facility","lineage":["https://openalex.org/I114772536","https://openalex.org/I74973139"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott McMillan","raw_affiliation_strings":["Software Engineering Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-1868-5178","affiliations":[{"raw_affiliation_string":"Software Engineering Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I114772536","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103044975","display_name":"Martin Schatz","orcid":"https://orcid.org/0000-0002-6059-0490"},"institutions":[{"id":"https://openalex.org/I3197470489","display_name":"Alpha Omega Alpha Medical Honor Society","ror":"https://ror.org/057q9nn35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3197470489"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin D. Schatz","raw_affiliation_strings":["Meta, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-6059-0490","affiliations":[{"raw_affiliation_string":"Meta, Menlo Park, USA","institution_ids":["https://openalex.org/I3197470489","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.08608365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9112111330032349},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.620693027973175},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5237683653831482},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.522072970867157},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.452130526304245},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.44071394205093384},{"id":"https://openalex.org/keywords/abstraction-layer","display_name":"Abstraction layer","score":0.4312695562839508},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4209057092666626},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3915322721004486},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35297441482543945},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33817851543426514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9112111330032349},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.620693027973175},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5237683653831482},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.522072970867157},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.452130526304245},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.44071394205093384},{"id":"https://openalex.org/C147358964","wikidata":"https://www.wikidata.org/wiki/Q1200992","display_name":"Abstraction layer","level":3,"score":0.4312695562839508},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4209057092666626},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3915322721004486},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35297441482543945},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33817851543426514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3607870","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607870","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3607870","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3607870","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G2144278397","display_name":null,"funder_award_id":"FA8702-15-D-0002","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"},{"id":"https://openalex.org/G3315187950","display_name":null,"funder_award_id":"Contract No. FA8702-15-D-0002","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"},{"id":"https://openalex.org/G526907975","display_name":null,"funder_award_id":"FA8702-15-D-0002","funder_id":"https://openalex.org/F4320310207","funder_display_name":"Carnegie Mellon University"},{"id":"https://openalex.org/G7665841296","display_name":null,"funder_award_id":"HR00112190099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320319290","display_name":"Meta","ror":null},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W111533445","https://openalex.org/W1549358575","https://openalex.org/W2002257715","https://openalex.org/W2038469228","https://openalex.org/W2073061372","https://openalex.org/W2084231858","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2252007067","https://openalex.org/W2412152731","https://openalex.org/W2516525699","https://openalex.org/W2612445135","https://openalex.org/W2798341898","https://openalex.org/W2804500013","https://openalex.org/W2896457183","https://openalex.org/W2912168260","https://openalex.org/W2999905431","https://openalex.org/W3037988796","https://openalex.org/W3082020764","https://openalex.org/W3141394081","https://openalex.org/W4297775537","https://openalex.org/W4301045096","https://openalex.org/W4311543031","https://openalex.org/W4384787681","https://openalex.org/W4385245566","https://openalex.org/W6632978964","https://openalex.org/W6687483927","https://openalex.org/W6739901393","https://openalex.org/W6752057402","https://openalex.org/W6782855247","https://openalex.org/W6792642166","https://openalex.org/W6797184042"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W1987014004","https://openalex.org/W3043327176","https://openalex.org/W4242666993","https://openalex.org/W2533779217"],"abstract_inverted_index":{"Interest":[0],"in":[1,13,206],"deploying":[2],"deep":[3],"neural":[4],"network":[5],"(DNN)":[6],"inference":[7,56],"on":[8,99,263],"edge":[9],"devices":[10],"has":[11],"resulted":[12],"an":[14,59,106],"explosion":[15],"of":[16,21,62,178,191,216,227,246,249],"the":[17,49,63,67,93,151,174,189,207,214,247,259,279],"number":[18],"and":[19,115,141,153,170,185,195,230,267,294],"types":[20,229],"hardware":[22,69],"platforms":[23,266],"that":[24,88,127,179,223,278],"machine":[25],"learning":[26],"(ML)":[27],"libraries":[28,87],"must":[29],"support.":[30],"High-level":[31],"programming":[32],"interfaces,":[33],"such":[34,290],"as":[35,291],"TensorFlow,":[36,292],"can":[37],"be":[38,210],"readily":[39],"ported":[40],"across":[41,102,146,193],"different":[42],"devices;":[43],"however,":[44],"maintaining":[45],"performance":[46,281],"when":[47],"porting":[48],"low-level":[50],"implementation":[51],"is":[52,128,164,235,252,282],"more":[53],"nuanced.":[54],"High-performance":[55],"implementations":[57],"require":[58,201],"effective":[60],"mapping":[61,73],"high-level":[64],"interface":[65],"to":[66,78,92,104,131,209,284],"target":[68,94],"platform.":[70,95],"Commonly,":[71],"this":[72,118,233],"may":[74],"use":[75],"optimizing":[76],"compilers":[77],"generate":[79],"code":[80,192],"at":[81],"compile":[82],"time":[83,152],"or":[84,285],"high-performance":[85,241],"vendor":[86],"have":[89,220],"been":[90],"specialized":[91],"Both":[96],"approaches":[97],"rely":[98],"expert":[100],"knowledge":[101],"levels":[103],"produce":[105],"efficient":[107],"mapping.":[108],"This":[109],"makes":[110],"supporting":[111],"new":[112,132],"architectures":[113,199],"difficult":[114],"time-consuming.":[116],"In":[117],"work,":[119],"we":[120,219],"present":[121],"a":[122,137,171,202,225],"DNN":[123,242],"library":[124],"framework,":[125],"SMaLL,":[126],"easily":[129,236],"extensible":[130,237],"architectures.":[133],"The":[134,181],"framework":[135,251],"uses":[136],"unified":[138,182],"loop":[139,183],"structure":[140,184],"shared,":[142],"cache-friendly":[143],"data":[144,158],"format":[145],"all":[147],"intermediate":[148],"layers,":[149],"eliminating":[150],"memory":[154],"overheads":[155],"incurred":[156],"by":[157,166,254],"transformation":[159],"between":[160],"layers.":[161],"Each":[162],"layer":[163,228],"implemented":[165],"specifying":[167],"its":[168],"dimensions":[169],"kernel":[172,186,208],",":[173],"key":[175],"computing":[176,196,231],"operation":[177],"layer.":[180],"abstraction":[187],"allows":[188],"reuse":[190],"layers":[194],"platforms.":[197],"New":[198],"only":[200],"few":[203],"hundred":[204],"lines":[205],"redesigned.":[211],"To":[212],"show":[213,277],"benefits":[215],"our":[217,250],"approach,":[218],"developed":[221],"software":[222,234],"supports":[224],"range":[226],"platforms;":[232],"for":[238],"rapidly":[239],"instantiating":[240,255],"libraries.":[243],"An":[244],"evaluation":[245],"portability":[248],"shown":[253],"end-to-end":[256,280],"networks":[257],"from":[258],"MLPerf:tiny":[260],"benchmark":[261],"suite":[262],"five":[264],"ARM":[265],"one":[268],"x86":[269],"platform":[270],"(an":[271],"AMD":[272],"Zen":[273],"2).":[274],"We":[275],"also":[276],"comparable":[283],"better":[286],"than":[287],"ML":[288],"frameworks":[289],"TVM,":[293],"LibTorch.":[295]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
