{"id":"https://openalex.org/W4399723097","doi":"https://doi.org/10.1145/3665283.3665294","title":"An End-to-End Programming Model for AI Engine Architectures","display_name":"An End-to-End Programming Model for AI Engine Architectures","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4399723097","doi":"https://doi.org/10.1145/3665283.3665294"},"language":"en","primary_location":{"id":"doi:10.1145/3665283.3665294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665283.3665294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"14th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART 24))","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://knowledge.uchicago.edu/record/12382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035054696","display_name":"Maksim Levental","orcid":"https://orcid.org/0009-0005-3450-2847"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maksim Levental","raw_affiliation_strings":["University of Chicago, United States"],"affiliations":[{"raw_affiliation_string":"University of Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057750373","display_name":"Arham Khan","orcid":"https://orcid.org/0009-0006-6960-6651"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arham Khan","raw_affiliation_strings":["University of Chicago, United States"],"affiliations":[{"raw_affiliation_string":"University of Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088145676","display_name":"Ryan Chard","orcid":"https://orcid.org/0000-0002-6781-7432"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Chard","raw_affiliation_strings":["Argonne National Laboratory, United States"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, United States","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago, United States"],"affiliations":[{"raw_affiliation_string":"University of Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014827775","display_name":"Stephen Neuendorffer","orcid":"https://orcid.org/0000-0003-2956-8428"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Neuendorffer","raw_affiliation_strings":["Advanced Micro Devices Inc., United States"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc., United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032231503","display_name":"Ian Foster","orcid":"https://orcid.org/0000-0003-2129-5269"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ian Foster","raw_affiliation_strings":["University of Chicago, United States"],"affiliations":[{"raw_affiliation_string":"University of Chicago, United States","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035054696"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67269904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9832000136375427,"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":0.9718000292778015,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6903935670852661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6839969158172607},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4563820958137512},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39825308322906494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2083360254764557}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6903935670852661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6839969158172607},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4563820958137512},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39825308322906494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2083360254764557}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3665283.3665294","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3665283.3665294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"14th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART 24))","raw_type":"proceedings-article"},{"id":"pmh:oai:uchicago.tind.io:12382","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/12382","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/12382","raw_type":"Text"},{"id":"doi:10.6082/uchicago.12382","is_oa":true,"landing_page_url":"https://doi.org/10.6082/uchicago.12382","pdf_url":null,"source":{"id":"https://openalex.org/S7407053018","display_name":"University of Chicago","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"thesis"}],"best_oa_location":{"id":"pmh:oai:uchicago.tind.io:12382","is_oa":true,"landing_page_url":"http://knowledge.uchicago.edu/record/12382","pdf_url":null,"source":{"id":"https://openalex.org/S4306402460","display_name":"Knowledge@UChicago (University of Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40347166","host_organization_name":"University of Chicago","host_organization_lineage":["https://openalex.org/I40347166"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://knowledge.uchicago.edu/record/12382","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W2046041890"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Coarse-Grained":[0],"Reconfigurable":[1],"Architectures":[2],"(CGRAs)":[3],"are":[4,25,62],"becoming":[5],"a":[6,50,93,97,140],"promising":[7],"alternative":[8],"to":[9,65,116,151,163,170,181],"conventional":[10],"computing":[11],"architectures":[12],"such":[13,41],"as":[14,42],"CPUs,":[15],"GPUs,":[16,30],"and":[17,22,29,45,74,96,119,138,155,165,176,184],"FPGAs":[18,68],"when":[19],"energy":[20],"efficiency":[21],"high":[23,94],"performance":[24,190],"required.":[26],"Like":[27],"CPUs":[28,73],"CGRAs":[31],"have":[32],"processing":[33],"elements":[34],"(PEs)":[35],"that":[36,160],"can":[37],"perform":[38],"complex":[39],"operations,":[40],"vectorized":[43],"arithmetic,":[44],"like":[46],"FPGAs,":[47],"they":[48,61],"support":[49],"reconfigurable":[51],"topology":[52],"of":[53,56,126],"components.":[54],"Because":[55],"their":[57],"coarser":[58],"grain":[59],"reconfigurability,":[60],"less":[63,174],"challenging":[64,71],"program":[66,171],"than":[67,72],"but":[69],"more":[70],"GPUs.":[75],"This":[76],"paper":[77],"presents":[78],"an":[79,145],"end-to-end":[80],"programming":[81,90,112,133,196],"model":[82,113,134],"for":[83,129,188],"AMD":[84],"AI":[85,194],"Engine":[86,195],"CGRAs,":[87],"which":[88],"enables":[89,168],"simultaneously":[91],"at":[92],"level":[95],"very":[98],"implementation-specific":[99],"level,":[100],"all":[101,106,182],"in":[102,107],"the":[103,108,123],"same":[104,109],"language,":[105],"\"flow\".":[110],"Our":[111],"allows":[114],"users":[115,169],"specify,":[117],"implement,":[118],"test":[120],"on-device,":[121],"enabling":[122],"productive":[124],"design":[125,167],"dataflow":[127],"programs":[128],"streaming":[130],"applications.":[131],"The":[132],"is":[135],"open":[136],"source":[137],"includes":[139],"language":[141,164],"frontend":[142],"(Python":[143],"eDSL),":[144],"MLIR":[146],"based":[147],"compiler,":[148],"export":[149],"paths":[150],"target":[152],"codegen":[153],"compilers,":[154],"runtime":[156],"infrastructure.":[157],"We":[158],"show":[159],"our":[161],"approach":[162],"compiler":[166],"with":[172,192],"much":[173],"friction":[175],"ceremony":[177],"while":[178],"preserving":[179],"access":[180],"features":[183],"device":[185],"APIs":[186],"necessary":[187],"achieving":[189],"competitive":[191],"existing":[193],"models.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}