{"id":"https://openalex.org/W4387968429","doi":"https://doi.org/10.1145/3630007","title":"Symphony: Orchestrating Sparse and Dense Tensors with Hierarchical Heterogeneous Processing","display_name":"Symphony: Orchestrating Sparse and Dense Tensors with Hierarchical Heterogeneous Processing","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4387968429","doi":"https://doi.org/10.1145/3630007"},"language":"en","primary_location":{"id":"doi:10.1145/3630007","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630007","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630007","source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3630007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009910914","display_name":"Michael Pellauer","orcid":"https://orcid.org/0000-0002-5305-4307"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Pellauer","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5305-4307","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056153489","display_name":"Jason Clemons","orcid":"https://orcid.org/0000-0001-5533-417X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Clemons","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5533-417X","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645479","display_name":"Vignesh Balaji","orcid":"https://orcid.org/0009-0003-0850-2363"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vignesh Balaji","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0009-0003-0850-2363","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060189926","display_name":"Neal Crago","orcid":"https://orcid.org/0000-0001-7774-0531"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neal Crago","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7774-0531","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078825915","display_name":"Aamer Jaleel","orcid":"https://orcid.org/0000-0002-5709-2992"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aamer Jaleel","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5709-2992","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991475","display_name":"Donghyuk Lee","orcid":"https://orcid.org/0009-0001-9572-5391"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghyuk Lee","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0009-0001-9572-5391","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055699570","display_name":"Mike O\u2019Connor","orcid":"https://orcid.org/0000-0003-0944-2393"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike O\u2019Connor","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0944-2393","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Angshuman Parashar","orcid":"https://orcid.org/0000-0001-9936-6501"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angshuman Parashar","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9936-6501","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005774998","display_name":"Sean Treichler","orcid":"https://orcid.org/0000-0003-2189-4026"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Treichler","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2189-4026","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080155613","display_name":"Po-An Tsai","orcid":"https://orcid.org/0000-0003-4561-6450"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-An Tsai","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4561-6450","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063354509","display_name":"Stephen W. Keckler","orcid":"https://orcid.org/0000-0001-6701-6099"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen W. Keckler","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6701-6099","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024384625","display_name":"Joel Emer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel S. Emer","raw_affiliation_strings":["NVIDIA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3459-5466","affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":1.8554,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85139069,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"41","issue":"1-4","first_page":"1","last_page":"30"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9904000163078308,"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"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.982699990272522,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8587105870246887},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6155198812484741},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5747714638710022},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.5664089918136597},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4722430408000946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8587105870246887},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6155198812484741},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5747714638710022},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.5664089918136597},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4722430408000946},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3630007","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630007","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630007","source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/152619","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/152619","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152619/1/3630007.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Association for Computing Machinery","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1145/3630007","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630007","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630007","source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968429.pdf","grobid_xml":"https://content.openalex.org/works/W4387968429.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1981943579","https://openalex.org/W1999085092","https://openalex.org/W2002555321","https://openalex.org/W2035080386","https://openalex.org/W2060736133","https://openalex.org/W2100430002","https://openalex.org/W2134237243","https://openalex.org/W2154790323","https://openalex.org/W2160566592","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2579963044","https://openalex.org/W2606722458","https://openalex.org/W2626211758","https://openalex.org/W2767274246","https://openalex.org/W2767588966","https://openalex.org/W2798652719","https://openalex.org/W2940862705","https://openalex.org/W2944576035","https://openalex.org/W2951135776","https://openalex.org/W2963806858","https://openalex.org/W2979310060","https://openalex.org/W2979340153","https://openalex.org/W2980104813","https://openalex.org/W2980119420","https://openalex.org/W2980200167","https://openalex.org/W2980270412","https://openalex.org/W2980612421","https://openalex.org/W2998732502","https://openalex.org/W3012204286","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3037261029","https://openalex.org/W3098303312","https://openalex.org/W3103188330","https://openalex.org/W3118608800","https://openalex.org/W3157055696","https://openalex.org/W3159869264","https://openalex.org/W3188321821","https://openalex.org/W3190854509","https://openalex.org/W3192225725","https://openalex.org/W3207932494","https://openalex.org/W4241140669","https://openalex.org/W4252563462","https://openalex.org/W4286571734","https://openalex.org/W4327911471","https://openalex.org/W4327930517"],"related_works":["https://openalex.org/W2489934651","https://openalex.org/W108401543","https://openalex.org/W2279642117","https://openalex.org/W4300190729","https://openalex.org/W2953056293","https://openalex.org/W4200143910","https://openalex.org/W2019374455","https://openalex.org/W1975522091","https://openalex.org/W1576429146","https://openalex.org/W2140286994"],"abstract_inverted_index":{"Sparse":[0],"tensor":[1,182],"algorithms":[2,78],"are":[3],"becoming":[4],"widespread,":[5],"particularly":[6],"in":[7],"the":[8,43,58,101,106,112,124,167],"domains":[9],"of":[10,61,77,85,103,114,123,159],"deep":[11],"learning,":[12],"graph":[13],"and":[14,17,49,87,117,152,156,164,184,189],"data":[15,36,59,104,116,118,143,150],"analytics,":[16],"scientific":[18],"computing.":[19],"Current":[20],"high-performance":[21],"broad-domain":[22],"architectures,":[23],"such":[24,146],"as":[25,67,147],"GPUs,":[26],"often":[27],"suffer":[28],"memory":[29,44,107,169],"system":[30],"inefficiencies":[31],"by":[32],"moving":[33,38],"too":[34,40],"much":[35],"or":[37,79],"it":[39],"far":[41],"through":[42],"hierarchy.":[45,170],"To":[46],"increase":[47],"performance":[48,179],"efficiency,":[50],"proposed":[51],"domain-specific":[52],"accelerators":[53],"tailor":[54],"their":[55],"architectures":[56],"to":[57,73,109],"needs":[60],"a":[62,68,74,83,94,194],"narrow":[63],"application":[64],"domain,":[65],"but":[66,139],"result":[69],"cannot":[70],"be":[71],"applied":[72],"wide":[75],"range":[76],"applications":[80],"that":[81,98,173],"contain":[82],"mix":[84],"sparse":[86,153,181],"dense":[88],"algorithms.":[89],"This":[90],"article":[91],"proposes":[92],"Symphony,":[93],"hybrid":[95],"programmable/specialized":[96],"architecture":[97,126],"focuses":[99],"on":[100,180],"orchestration":[102,144],"throughout":[105,166],"hierarchy":[108],"simultaneously":[110],"reduce":[111],"movement":[113,119],"unnecessary":[115],"distances.":[120],"Key":[121],"elements":[122],"Symphony":[125,174],"include":[127],"(1)":[128],"specialized":[129],"reconfigurable":[130],"units":[131],"aimed":[132],"not":[133],"only":[134],"at":[135,141],"roofline":[136],"floating-point":[137],"computations":[138],"also":[140],"supporting":[142],"features,":[145],"address":[148],"generation,":[149],"filtering,":[151],"metadata":[154],"processing;":[155],"(2)":[157],"distribution":[158],"computation":[160],"resources":[161],"(both":[162],"programmable":[163],"specialized)":[165],"on-chip":[168],"We":[171],"demonstrate":[172],"can":[175],"match":[176],"non-programmable":[177],"ASIC":[178],"algebra":[183],"provide":[185],"31\u00d7":[186],"improved":[187,191],"runtime":[188],"44\u00d7":[190],"energy":[192],"over":[193],"comparably":[195],"provisioned":[196],"GPU":[197],"for":[198],"these":[199],"applications.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}