{"id":"https://openalex.org/W4394661856","doi":"https://doi.org/10.1145/3656401","title":"Allo: A Programming Model for Composable Accelerator Design","display_name":"Allo: A Programming Model for Composable Accelerator Design","publication_year":2024,"publication_date":"2024-06-20","ids":{"openalex":"https://openalex.org/W4394661856","doi":"https://doi.org/10.1145/3656401"},"language":"en","primary_location":{"id":"doi:10.1145/3656401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656401","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656401","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3656401","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008694159","display_name":"Hongzheng Chen","orcid":"https://orcid.org/0000-0002-6617-0075"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzheng Chen","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0002-6617-0075","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059293268","display_name":"Niansong Zhang","orcid":"https://orcid.org/0000-0002-2850-0176"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niansong Zhang","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0002-2850-0176","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032824854","display_name":"Shaojie Xiang","orcid":"https://orcid.org/0000-0002-6901-8837"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojie Xiang","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0002-6901-8837","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023357588","display_name":"Zhichen Zeng","orcid":"https://orcid.org/0009-0005-0023-2367"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichen Zeng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0005-0023-2367","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997939","display_name":"Mengjia Dai","orcid":"https://orcid.org/0000-0002-7347-5117"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjia Dai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7347-5117","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["Cornell University, Ithaca, USA"],"raw_orcid":"https://orcid.org/0000-0002-0778-0308","affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.4407,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.99677099,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8","issue":"PLDI","first_page":"593","last_page":"620"},"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":0.9994000196456909,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8150119781494141},{"id":"https://openalex.org/keywords/high-level-synthesis","display_name":"High-level synthesis","score":0.5585708618164062},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5199567079544067},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.48143547773361206},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.47659605741500854},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4598056375980377},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4517856538295746},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.42028310894966125},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32234910130500793},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.321940541267395},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2853772044181824},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2296161949634552},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16378462314605713},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.14393869042396545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150119781494141},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.5585708618164062},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5199567079544067},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.48143547773361206},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.47659605741500854},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4598056375980377},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4517856538295746},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.42028310894966125},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32234910130500793},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.321940541267395},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2853772044181824},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2296161949634552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16378462314605713},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.14393869042396545},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3656401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656401","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656401","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2404.04815","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.04815","pdf_url":"https://arxiv.org/pdf/2404.04815","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3656401","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3656401","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3656401","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1452086972","display_name":null,"funder_award_id":"JUMP 2.0","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G2929905519","display_name":"Collaborative Research: FMitF: Track I: DeepSmith: Scheduling with Quality Guarantees for Efficient DNN Model Execution","funder_award_id":"2019306","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7564846446","display_name":null,"funder_award_id":"2118709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394661856.pdf"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W1980208272","https://openalex.org/W1983394510","https://openalex.org/W2024381286","https://openalex.org/W2046213250","https://openalex.org/W2110848488","https://openalex.org/W2124153277","https://openalex.org/W2141280299","https://openalex.org/W2163976959","https://openalex.org/W2166029537","https://openalex.org/W2194775991","https://openalex.org/W2466242877","https://openalex.org/W2590246587","https://openalex.org/W2606722458","https://openalex.org/W2607067159","https://openalex.org/W2771210328","https://openalex.org/W2788102204","https://openalex.org/W2791673912","https://openalex.org/W2798084934","https://openalex.org/W2798482398","https://openalex.org/W2898231337","https://openalex.org/W2899644485","https://openalex.org/W2899691047","https://openalex.org/W2905135312","https://openalex.org/W2906737788","https://openalex.org/W2950001020","https://openalex.org/W2979826702","https://openalex.org/W2987684178","https://openalex.org/W3007436455","https://openalex.org/W3011239338","https://openalex.org/W3027723509","https://openalex.org/W3033414614","https://openalex.org/W3033664232","https://openalex.org/W3047158069","https://openalex.org/W3090487264","https://openalex.org/W3101493857","https://openalex.org/W3101543398","https://openalex.org/W3108085245","https://openalex.org/W3112630515","https://openalex.org/W3122286897","https://openalex.org/W3130920634","https://openalex.org/W3131252192","https://openalex.org/W3133395503","https://openalex.org/W3149736422","https://openalex.org/W3155384757","https://openalex.org/W3200826900","https://openalex.org/W3205717712","https://openalex.org/W3210312974","https://openalex.org/W3210943174","https://openalex.org/W3213528054","https://openalex.org/W4205983429","https://openalex.org/W4211118386","https://openalex.org/W4224265992","https://openalex.org/W4226199141","https://openalex.org/W4229673714","https://openalex.org/W4242577057","https://openalex.org/W4242726609","https://openalex.org/W4245440340","https://openalex.org/W4246166885","https://openalex.org/W4249075482","https://openalex.org/W4251637954","https://openalex.org/W4281707342","https://openalex.org/W4285171882","https://openalex.org/W4292119927","https://openalex.org/W4293024053","https://openalex.org/W4293025825","https://openalex.org/W4308083513","https://openalex.org/W4318541538","https://openalex.org/W4321637375","https://openalex.org/W4366850868","https://openalex.org/W4380874786","https://openalex.org/W4393579185","https://openalex.org/W4393949386","https://openalex.org/W4394998532","https://openalex.org/W4394998694","https://openalex.org/W6846659131","https://openalex.org/W6930189123"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2147358386","https://openalex.org/W3195293013"],"abstract_inverted_index":{"Special-purpose":[0],"hardware":[1,122],"accelerators":[2],"are":[3,75],"increasingly":[4],"pivotal":[5],"for":[6,91,115],"sustaining":[7],"performance":[8],"improvements":[9],"in":[10,37,78,158,203],"emerging":[11],"applications,":[12],"especially":[13],"as":[14,137],"the":[15,58,100,145,204,207,210,214,226,240],"benefits":[16],"of":[17,55,60,140,148,213,242],"technology":[18],"scaling":[19],"continue":[20],"to":[21,31,51,68,244],"diminish.":[22],"However,":[23],"designers":[24],"currently":[25],"lack":[26],"effective":[27,90],"tools":[28,45,196],"and":[29,128,134,181,197],"methodologies":[30],"construct":[32],"complex,":[33],"high-performance":[34],"accelerator":[35,63,118,217],"architectures":[36],"a":[38,83,111,138,159],"productive":[39],"manner.":[40,162],"Existing":[41,86],"high-level":[42],"synthesis":[43],"(HLS)":[44],"often":[46],"require":[47],"intrusive":[48],"sourcelevel":[49],"changes":[50],"attain":[52],"satisfactory":[53],"quality":[54],"results.":[56],"Despite":[57],"introduction":[59],"several":[61,182],"new":[62],"design":[64,101],"languages":[65],"(ADLs)":[66],"aiming":[67],"enhance":[69],"or":[70],"replace":[71],"HLS,":[72],"their":[73],"advantages":[74],"more":[76],"evident":[77],"relatively":[79],"simple":[80],"applications":[81],"with":[82,95,230],"single":[84],"kernel.":[85],"ADLs":[87,198],"prove":[88],"less":[89],"realistic":[92,183],"hierarchical":[93,146],"designs":[94],"multiple":[96],"kernels,":[97],"even":[98],"if":[99],"hierarchy":[102],"is":[103,218],"flattened.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108],"introduce":[109],"Allo,":[110],"composable":[112],"programming":[113],"model":[114],"efficient":[116],"spatial":[117],"design.":[119],"Allo":[120,143,191,215,243],"decouples":[121],"customizations,":[123],"including":[124],"compute,":[125],"memory,":[126],"communication,":[127],"data":[129],"type":[130],"from":[131,155],"algorithm":[132],"specification,":[133],"encapsulates":[135],"them":[136],"set":[139],"customization":[141],"primitives.":[142],"preserves":[144],"structure":[147],"an":[149],"input":[150],"program":[151],"by":[152],"combining":[153],"customizations":[154],"different":[156],"functions":[157],"bottomup,":[160],"type-safe":[161],"This":[163],"approach":[164],"facilitates":[165],"holistic":[166],"optimizations":[167],"that":[168,190],"span":[169],"across":[170],"function":[171],"boundaries.":[172],"We":[173],"conduct":[174],"comprehensive":[175],"experiments":[176],"on":[177,199],"commonly-used":[178],"HLS":[179,195],"benchmarks":[180],"deep":[184],"learning":[185],"models.":[186],"Our":[187],"evaluation":[188],"shows":[189],"can":[192],"outperform":[193],"state-of-the-art":[194],"all":[200],"test":[201],"cases":[202],"PolyBench.":[205],"For":[206],"GPT2":[208],"model,":[209],"inference":[211],"latency":[212],"generated":[216],"<mml:math":[219,231],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[220,232],"display=\"inline\">":[221,233],"<mml:mn>1.7\u00d7</mml:mn>":[222],"</mml:math>":[223,235],"faster":[224],"than":[225],"NVIDIA":[227],"A100":[228],"GPU":[229],"<mml:mn>5.4\u00d7</mml:mn>":[234],"higher":[236],"energy":[237],"efficiency,":[238],"demonstrating":[239],"capability":[241],"handle":[245],"large-scale":[246],"designs.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}