{"id":"https://openalex.org/W4211149354","doi":"https://doi.org/10.1145/3490422.3510453","title":"The Virtuous Cycles of Determinism: Programming Groq's Tensor Streaming Processor","display_name":"The Virtuous Cycles of Determinism: Programming Groq's Tensor Streaming Processor","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4211149354","doi":"https://doi.org/10.1145/3490422.3510453"},"language":"en","primary_location":{"id":"doi:10.1145/3490422.3510453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3510453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5109562655","display_name":"Satnam Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satnam Singh","raw_affiliation_strings":["Groq Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Groq Inc., Mountain View, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109562655"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01583528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9987000226974487,"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":0.8016312122344971},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6574770212173462},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6296587586402893},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5737637877464294},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.5607471466064453},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5117101669311523},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5113677382469177},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5002977848052979},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4384092390537262},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42413944005966187},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35304129123687744},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16633522510528564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016312122344971},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6574770212173462},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6296587586402893},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5737637877464294},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.5607471466064453},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5117101669311523},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5113677382469177},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5002977848052979},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4384092390537262},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42413944005966187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35304129123687744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16633522510528564},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490422.3510453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3510453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3160830781"],"related_works":["https://openalex.org/W3108739929","https://openalex.org/W2563372350","https://openalex.org/W4234072317","https://openalex.org/W2016731656","https://openalex.org/W2791650676","https://openalex.org/W1491222299","https://openalex.org/W2304162915","https://openalex.org/W1549543749","https://openalex.org/W2965891118","https://openalex.org/W2305320569"],"abstract_inverted_index":{"FPGAs":[0],"and":[1,4,29,48,73,88,150,161,175,193,228],"other":[2,44],"2D":[3],"3D":[5],"spatial":[6,45,57],"computing":[7,16,46,58,173,203],"fabrics":[8,47],"share":[9],"several":[10],"common":[11,50,78],"characteristics":[12,68],"e.g.":[13,27],"a":[14,104,129,157,166,178],"deterministic":[15,202],"model":[17,76],"with":[18,226],"distributed":[19],"memories,":[20],"but":[21],"also":[22],"differ":[23],"along":[24],"important":[25],"dimensions":[26],"granularity":[28],"communication":[30],"infrastructure.":[31],"This":[32],"talk":[33,81],"will":[34,82,106,205],"position":[35],"Groq's":[36,123],"Tensor":[37],"Streaming":[38],"Processing":[39],"(TSP)":[40],"chip":[41,183],"relative":[42],"to":[43,95,108,119],"highlight":[49],"aspects":[51],"of":[52,65,69,92,111,115,132,201],"programming":[53,75],"models":[54,204],"for":[55],"such":[56],"engines":[59],"as":[60,62,189,208],"well":[61],"highlighting":[63],"some":[64],"the":[66,70,90,112,116,120],"unique":[67],"TSP":[71,121,124,224],"architecture":[72,125],"its":[74],"One":[77],"characteristic":[79],"this":[80],"focus":[83],"on":[84,128,186,223],"is":[85,126,162],"\\em":[86],"determinism":[87],"specifically":[89],"use":[91],"static":[93],"scheduling":[94,227],"know":[96],"at":[97],"compile":[98],"time":[99],"exactly":[100],"how":[101],"many":[102],"cycles":[103],"program":[105],"take":[107],"execute":[109],"regardless":[110],"specific":[113],"values":[114],"input":[117],"data":[118],"chip.":[122],"based":[127],"parallel":[130],"collection":[131],"coarse":[133],"grain":[134],"processing":[135],"units":[136],"including":[137],"matrix":[138],"multiplication":[139],"or":[140,171],"convolution":[141],"(MXM),":[142],"vector":[143,147],"operations":[144],"(VXM),":[145],"arbitrary":[146],"transformations":[148],"(SXM)":[149],"various":[151],"numerical":[152],"operations.":[153],"Data":[154],"originates":[155],"from":[156],"memory":[158,179],"reads":[159],"(MEM)":[160],"then":[163],"chained":[164],"through":[165,169],"tensor":[167],"pipeline":[168],"one":[170],"more":[172],"blocks":[174],"terminated":[176],"by":[177,231],"write":[180],"(MEM).":[181],"The":[182],"can":[184,220],"operate":[185],"in-flight":[187],"tensors":[188],"they":[190],"are":[191],"produced":[192],"consumed,":[194],"aggressively":[195],"exploiting":[196],"data-flow":[197],"locality.":[198],"A":[199],"variety":[200],"be":[206,221],"surveyed":[207],"we":[209],"seek":[210],"abstractions":[211],"that":[212],"support":[213],"rapid":[214],"multiplexing":[215],"between":[216],"multiple":[217],"workloads":[218],"which":[219],"co-resident":[222],"chips,":[225],"coordination":[229],"facilitated":[230],"determinism.":[232]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}