{"id":"https://openalex.org/W4400579944","doi":"https://doi.org/10.1109/mm.2024.3423750","title":"DNNDaSher: A Compiler Framework for Dataflow Compatible End-to-End Acceleration on IBM AIU","display_name":"DNNDaSher: A Compiler Framework for Dataflow Compatible End-to-End Acceleration on IBM AIU","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400579944","doi":"https://doi.org/10.1109/mm.2024.3423750"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2024.3423750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3423750","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-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/A5021284824","display_name":"Sanchari Sen","orcid":"https://orcid.org/0000-0003-0080-2882"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanchari Sen","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086674756","display_name":"Shubham Jain","orcid":"https://orcid.org/0000-0002-2291-7712"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Jain","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075611664","display_name":"Sarada Krithivasan","orcid":"https://orcid.org/0000-0002-2958-1377"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarada Krithivasan","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056502880","display_name":"Vijayalakshmi Srinivasan","orcid":"https://orcid.org/0000-0001-6958-3855"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayalakshmi Srinivasan","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM Research, Yorktown Heights, NY, United States"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, United States","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5021284824"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09532925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"6","first_page":"63","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9861000180244446,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9861000180244446,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9847000241279602,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9810000061988831,"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/dataflow","display_name":"Dataflow","score":0.8845126032829285},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6791038513183594},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.596947431564331},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.571034848690033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5636909008026123},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3276323676109314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.32239577174186707},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.18318331241607666},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1358489990234375}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8845126032829285},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6791038513183594},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.596947431564331},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.571034848690033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5636909008026123},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3276323676109314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32239577174186707},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.18318331241607666},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1358489990234375},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2024.3423750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2024.3423750","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W3187235458","https://openalex.org/W4244024631","https://openalex.org/W4288083528","https://openalex.org/W4380874786","https://openalex.org/W4392745848","https://openalex.org/W6771656455"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2907307640"],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"unit":[2],"(AIU)":[3],"is":[4,54],"a":[5,24,52,69,79],"specialized":[6],"accelerator":[7],"card":[8],"from":[9],"IBM":[10],"offering":[11],"state-of-the-art":[12],"compute":[13,20],"capabilities":[14],"(hundreds":[15],"of":[16,27,114,122],"tera-operations)":[17],"through":[18],"dataflow-driven":[19],"arrays":[21],"attached":[22],"to":[23,82,92,101,108,118],"multilevel":[25],"hierarchy":[26],"distributed":[28],"memory":[29,57,99,115],"elements.":[30],"In":[31],"mapping":[32],"entire":[33],"AI":[34],"models,":[35],"functional":[36],"correctness":[37],"hinges":[38],"on":[39,139,143],"maintaining":[40],"dataflow":[41,85],"compatibility":[42],"between":[43],"producer\u2013consumer":[44],"operations,":[45],"i.e.,":[46],"the":[47,60,64,103,144],"element":[48],"organization":[49,61],"with":[50],"which":[51],"tensor":[53,94],"produced":[55],"in":[56,72],"must":[58],"match":[59],"expected":[62],"by":[63],"consumer(s).":[65],"This":[66],"paper":[67],"presents":[68],"key":[70],"component":[71],"AIU\u2019s":[73],"compiler":[74],"stack,":[75],"DNN":[76],"Data-Shuffler":[77],"(DnnDaSher),":[78],"systematic":[80],"framework":[81],"analyze":[83],"such":[84],"incompatibilities":[86],"and":[87,111,127],"invoke":[88],"an":[89],"intermediate":[90],"operation":[91],"shuffle":[93],"elements":[95,100],"within":[96],"and/or":[97],"across":[98],"resolve":[102],"discrepancy.":[104],"It":[105],"targets":[106],"opportunities":[107],"eliminate":[109],"shuffles":[110],"increase":[112],"granularity":[113],"accesses.":[116],"Compared":[117],"well-optimized":[119],"baseline":[120],"implementations":[121],"four":[123],"Convolutional":[124],"Neural":[125],"Networks":[126],"Transformer":[128],"benchmarks,":[129],"DNNDaSher":[130],"achieves":[131],"1.27\u00d7\u20134.12\u00d7":[132],"(average":[133],"2.3\u00d7)":[134],"end-to-end":[135],"latency":[136],"improvement":[137],"based":[138],"measured":[140],"execution":[141],"cycles":[142],"AIU.":[145]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}