{"id":"https://openalex.org/W4281823623","doi":"https://doi.org/10.1145/3470496.3533040","title":"The Mozart reuse exposed dataflow processor for AI and beyond","display_name":"The Mozart reuse exposed dataflow processor for AI and beyond","publication_year":2022,"publication_date":"2022-05-31","ids":{"openalex":"https://openalex.org/W4281823623","doi":"https://doi.org/10.1145/3470496.3533040"},"language":"en","primary_location":{"id":"doi:10.1145/3470496.3533040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3470496.3533040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028943049","display_name":"Karthikeyan Sankaralingam","orcid":"https://orcid.org/0000-0002-8315-2389"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karthikeyan Sankaralingam","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006723758","display_name":"Tony Nowatzki","orcid":"https://orcid.org/0000-0001-8483-3824"},"institutions":[{"id":"https://openalex.org/I2799798094","display_name":"UCLA Health","ror":"https://ror.org/01d88se56","country_code":"US","type":"funder","lineage":["https://openalex.org/I2799798094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tony Nowatzki","raw_affiliation_strings":["UCLA"],"affiliations":[{"raw_affiliation_string":"UCLA","institution_ids":["https://openalex.org/I2799798094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088199164","display_name":"Vinay Gangadhar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinay Gangadhar","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067114335","display_name":"Preyas Shah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Preyas Shah","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048327749","display_name":"Michael A. Davies","orcid":"https://orcid.org/0000-0002-0977-0912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Davies","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040041171","display_name":"William Galliher","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William Galliher","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100948241","display_name":"Ziliang Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziliang Guo","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051070128","display_name":"Jitu Khare","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitu Khare","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061553014","display_name":"Deepak Vijay","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deepak Vijay","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018773223","display_name":"Poly Palamuttam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Poly Palamuttam","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043730972","display_name":"Maghawan Punde","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maghawan Punde","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112588840","display_name":"Alex Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Tan","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084674044","display_name":"Vijay Thiruvengadam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay Thiruvengadam","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027082437","display_name":"Rongyi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongyi Wang","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047012483","display_name":"Shunmiao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunmiao Xu","raw_affiliation_strings":["SimpleMachines Inc"],"affiliations":[{"raw_affiliation_string":"SimpleMachines Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5028943049"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6329,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93616229,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"978","last_page":"992"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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":0.9965000152587891,"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":0.8597713112831116},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7811076641082764},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6534439921379089},{"id":"https://openalex.org/keywords/dataflow-architecture","display_name":"Dataflow architecture","score":0.5528146028518677},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5039674639701843},{"id":"https://openalex.org/keywords/debugger","display_name":"Debugger","score":0.46817487478256226},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4595218598842621},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.4579763114452362},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4275122582912445},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3785553574562073},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.3142712414264679},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.308879554271698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597713112831116},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7811076641082764},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6534439921379089},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.5528146028518677},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5039674639701843},{"id":"https://openalex.org/C2778485113","wikidata":"https://www.wikidata.org/wiki/Q193231","display_name":"Debugger","level":3,"score":0.46817487478256226},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4595218598842621},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.4579763114452362},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4275122582912445},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3785553574562073},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.3142712414264679},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.308879554271698}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3470496.3533040","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3470496.3533040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1982205631","https://openalex.org/W2035924020","https://openalex.org/W2055312318","https://openalex.org/W2105339504","https://openalex.org/W2150618958","https://openalex.org/W2152839228","https://openalex.org/W2170382128","https://openalex.org/W2295598076","https://openalex.org/W2318354022","https://openalex.org/W2725159389","https://openalex.org/W2804032941","https://openalex.org/W2808768830","https://openalex.org/W2897997157","https://openalex.org/W2941922059","https://openalex.org/W2945146780","https://openalex.org/W2950656546","https://openalex.org/W2951894856","https://openalex.org/W2953184160","https://openalex.org/W2962760690","https://openalex.org/W2980270412","https://openalex.org/W3004659153","https://openalex.org/W3016769527","https://openalex.org/W3036878841","https://openalex.org/W3040646053","https://openalex.org/W3042416028","https://openalex.org/W3082020764","https://openalex.org/W3117961507","https://openalex.org/W3154028478","https://openalex.org/W3157391606","https://openalex.org/W3186615785","https://openalex.org/W3187188899","https://openalex.org/W3190062760","https://openalex.org/W3192225725","https://openalex.org/W3192336523","https://openalex.org/W3213111742","https://openalex.org/W4214725219","https://openalex.org/W4230989867","https://openalex.org/W4245145882","https://openalex.org/W4312996980"],"related_works":["https://openalex.org/W2564598376","https://openalex.org/W1484403103","https://openalex.org/W2584408851","https://openalex.org/W2115158825","https://openalex.org/W2101960124","https://openalex.org/W4377693460","https://openalex.org/W2783505431","https://openalex.org/W2521947294","https://openalex.org/W2070353846","https://openalex.org/W1983889548"],"abstract_inverted_index":{"In":[0,123],"this":[1,118],"paper":[2,53],"we":[3],"introduce":[4],"the":[5,38,55,58,61,104,125,203],"Mozart":[6,179],"Processor,":[7],"which":[8],"implements":[9],"a":[10,21,85,107,140,144,168,198,207,211],"new":[11],"processing":[12],"paradigm":[13],"called":[14],"Reuse":[15],"Exposed":[16],"Dataflow":[17,33],"(RED).":[18],"RED":[19],"is":[20,74,180],"counterpart":[22],"to":[23,75,128,130,135,165],"existing":[24],"execution":[25],"models":[26],"of":[27,60,87,100,147,200,206],"Von-Neumann,":[28],"SIMT,":[29],"Dataflow,":[30],"and":[31,34,50,68,152,160,163,214],"FPGA.":[32],"data":[35],"reuse":[36],"are":[37],"fundamental":[39],"architecture":[40,114,209],"primitives":[41],"in":[42,121,210],"RED,":[43],"implemented":[44,157],"with":[45,117,158,177,197],"mechanisms":[46],"for":[47,84,106,143,216],"inter-worker":[48],"communication":[49],"synchronization.":[51],"The":[52,71,113,154],"defines":[54],"processor":[56],"architecture,":[57],"details":[59],"microarchitecture,":[62],"chip":[63,155],"implementation,":[64],"software":[65,94,110],"stack":[66],"development,":[67],"performance":[69],"results.":[70],"architecture's":[72],"goal":[73,92,126],"achieve":[76],"near-CPU":[77],"like":[78],"flexibility":[79,151],"while":[80,149,188],"having":[81],"ASIC-like":[82],"efficiency":[83],"large-class":[86],"data-intensive":[88],"workloads.":[89],"An":[90],"additional":[91],"was":[93,115,127,156],"maturity":[95],"---":[96,137],"have":[97],"large":[98,145],"coverage":[99],"applications":[101],"immediately,":[102],"avoiding":[103],"need":[105],"long-drawn":[108],"hand-tuning":[109],"development":[111],"phase.":[112],"defined":[116],"software-maturity/compiler":[119],"friendliness":[120],"mind.":[122],"short,":[124],"do":[129],"GPUs,":[131],"what":[132],"GPUs":[133,186],"did":[134],"CPUs":[136],"i.e.":[138],"be":[139],"better":[141,183],"solution":[142],"range":[146],"workloads,":[148],"preserving":[150],"programmability.":[153],"HBM":[159],"PCIe":[161],"interfaces":[162],"taken":[164],"production":[166],"on":[167],"16nm":[169],"TSMC":[170],"FFC":[171],"process.":[172],"For":[173],"ML":[174],"inference":[175],"tasks":[176],"batch-size=4,":[178],"integer":[181],"factors":[182],"than":[184],"state-of-the-art":[185],"even":[187],"being":[189],"nearly":[190],"2":[191],"technology":[192],"nodes":[193],"behind.":[194],"We":[195],"conclude":[196],"set":[199],"lessons":[201],"learned,":[202],"unique":[204],"challenges":[205],"clean-slate":[208],"commercial":[212],"setting,":[213],"pointers":[215],"uncovered":[217],"research":[218],"problems.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
