{"id":"https://openalex.org/W2967893498","doi":"https://doi.org/10.1145/3431388","title":"Exploiting Parallelism Opportunities with Deep Learning Frameworks","display_name":"Exploiting Parallelism Opportunities with Deep Learning Frameworks","publication_year":2020,"publication_date":"2020-12-30","ids":{"openalex":"https://openalex.org/W2967893498","doi":"https://doi.org/10.1145/3431388","mag":"2967893498"},"language":"en","primary_location":{"id":"doi:10.1145/3431388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431388","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3431388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051777475","display_name":"Yu Emma Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Emma Wang","raw_affiliation_strings":["Harvard University, Cambridge, MA","Harvard University , Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University , Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028220093","display_name":"Carole-Jean Wu","orcid":"https://orcid.org/0000-0002-9032-7239"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Carole-Jean Wu","raw_affiliation_strings":["Facebook AI","Facebook AI;"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI;","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382658","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0002-2945-9240"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Facebook AI","Facebook AI;"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI;","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046756907","display_name":"Kim Hazelwood","orcid":"https://orcid.org/0000-0002-2713-8507"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kim Hazelwood","raw_affiliation_strings":["Facebook AI","Facebook AI;"],"affiliations":[{"raw_affiliation_string":"Facebook AI","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI;","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026496503","display_name":"David Brooks","orcid":"https://orcid.org/0000-0002-0662-7889"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Brooks","raw_affiliation_strings":["Harvard University, Cambridge, MA","Harvard University , Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]},{"raw_affiliation_string":"Harvard University , Cambridge, MA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051777475"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.7072,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65529395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":"1","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9980999827384949,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9980999827384949,"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":0.8431267738342285},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7163689732551575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.705469012260437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7025565505027771},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6637451648712158},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6007745265960693},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5934014916419983},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42725250124931335},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41444239020347595},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.15856137871742249},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15162280201911926}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8431267738342285},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7163689732551575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.705469012260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7025565505027771},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6637451648712158},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6007745265960693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5934014916419983},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42725250124931335},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41444239020347595},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.15856137871742249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15162280201911926},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3431388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431388","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"},{"id":"pmh:oai:arXiv.org:1908.04705","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.04705","pdf_url":"https://arxiv.org/pdf/1908.04705","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2967893498","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.04705.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.04705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.04705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3431388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3431388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3431388","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":[],"awards":[{"id":"https://openalex.org/G1094271263","display_name":null,"funder_award_id":"CCF-1533737","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4493967758","display_name":null,"funder_award_id":"1533737","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2967893498.pdf","grobid_xml":"https://content.openalex.org/works/W2967893498.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2013062050","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2120575449","https://openalex.org/W2155893237","https://openalex.org/W2178615544","https://openalex.org/W2183341477","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2402144811","https://openalex.org/W2512971201","https://openalex.org/W2549139847","https://openalex.org/W2605350416","https://openalex.org/W2761434131","https://openalex.org/W2786320458","https://openalex.org/W2794670651","https://openalex.org/W2804032941","https://openalex.org/W2900810680","https://openalex.org/W2902741215","https://openalex.org/W2931743911","https://openalex.org/W2944745903","https://openalex.org/W2947737663","https://openalex.org/W2949017472","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963674387","https://openalex.org/W2985232804","https://openalex.org/W2986124642","https://openalex.org/W3008591352"],"related_works":["https://openalex.org/W3115348505","https://openalex.org/W2742765194","https://openalex.org/W3210871626","https://openalex.org/W2593773834","https://openalex.org/W3163671426","https://openalex.org/W2889494520","https://openalex.org/W2786013445","https://openalex.org/W2297238749","https://openalex.org/W3012276096","https://openalex.org/W2786320458","https://openalex.org/W2584763657","https://openalex.org/W2009537245","https://openalex.org/W2896550391","https://openalex.org/W3174716098","https://openalex.org/W3209444800","https://openalex.org/W1993320880","https://openalex.org/W2944260437","https://openalex.org/W3014979526","https://openalex.org/W3193789877","https://openalex.org/W3081960887"],"abstract_inverted_index":{"State-of-the-art":[0],"machine":[1,15,26,70],"learning":[2,16,27,71,109],"frameworks":[3],"support":[4],"a":[5,13,32,40,56,69,85,103],"wide":[6],"variety":[7],"of":[8,43,64,77,88,106],"design":[9,66],"features":[10,67],"to":[11,20,94],"enable":[12],"flexible":[14],"programming":[17],"interface":[18],"and":[19,30,47,73,81,99,124,130],"ease":[21],"the":[22,61,75,111,116,122],"programmability":[23],"burden":[24],"on":[25,50],"developers.":[28],"Identifying":[29],"using":[31],"performance-optimal":[33],"setting":[34],"in":[35,68],"feature-rich":[36],"frameworks,":[37],"however,":[38],"involves":[39],"non-trivial":[41],"amount":[42],"performance":[44,62,118],"profiling":[45],"efforts":[46],"often":[48],"relies":[49],"domain-specific":[51],"knowledge.":[52],"This":[53],"article":[54],"takes":[55],"deep":[57,108],"dive":[58],"into":[59,84],"analyzing":[60],"impact":[63],"key":[65],"framework":[72],"quantifies":[74],"role":[76],"parallelism.":[78],"The":[79],"observations":[80],"insights":[82],"distill":[83],"simple":[86],"set":[87,105],"guidelines":[89,120],"that":[90,115],"one":[91],"can":[92],"use":[93],"achieve":[95],"much":[96],"higher":[97],"training":[98],"inference":[100],"speedup.":[101],"Across":[102],"diverse":[104],"real-world":[107],"models,":[110],"evaluation":[112],"results":[113],"show":[114],"proposed":[117],"tuning":[119],"outperform":[121],"Intel":[123],"TensorFlow":[125],"recommended":[126],"settings":[127],"by":[128],"1.30\u00d7":[129],"1.38\u00d7,":[131],"respectively.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}