{"id":"https://openalex.org/W4310251122","doi":"https://doi.org/10.1145/3572908","title":"Unified Buffer: Compiling Image Processing and Machine Learning Applications to Push-Memory Accelerators","display_name":"Unified Buffer: Compiling Image Processing and Machine Learning Applications to Push-Memory Accelerators","publication_year":2022,"publication_date":"2022-11-29","ids":{"openalex":"https://openalex.org/W4310251122","doi":"https://doi.org/10.1145/3572908"},"language":"en","primary_location":{"id":"doi:10.1145/3572908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572908","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3572908","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102796221","display_name":"Qiaoyi Liu","orcid":"https://orcid.org/0000-0003-1083-9953"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiaoyi Liu","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033365763","display_name":"Jeff Setter","orcid":"https://orcid.org/0000-0002-2327-646X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Setter","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052101520","display_name":"Dillon Huff","orcid":"https://orcid.org/0000-0001-9055-3490"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dillon Huff","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072020797","display_name":"Maxwell Strange","orcid":"https://orcid.org/0000-0001-5945-1349"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxwell Strange","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072800422","display_name":"Kathleen Feng","orcid":"https://orcid.org/0000-0001-9860-4942"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathleen Feng","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090469068","display_name":"Mark Horowitz","orcid":"https://orcid.org/0000-0003-3245-7542"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Horowitz","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029554261","display_name":"Priyanka Raina","orcid":"https://orcid.org/0000-0002-8834-8663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyanka Raina","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041886781","display_name":"Fredrik Kj\u00f8lstad","orcid":"https://orcid.org/0000-0002-2267-903X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fredrik Kjolstad","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102796221"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":3.9679,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94505297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"20","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"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":0.8934423923492432},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6611430644989014},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5637253522872925},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5143819451332092},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.416718989610672},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4063414931297302},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36499348282814026},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2967589497566223},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19098547101020813},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.16035586595535278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8934423923492432},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6611430644989014},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5637253522872925},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5143819451332092},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.416718989610672},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4063414931297302},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36499348282814026},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2967589497566223},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19098547101020813},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.16035586595535278}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572908","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3572908","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572908","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572908","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G7716153948","display_name":null,"funder_award_id":"DSSoC","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8793294907","display_name":null,"funder_award_id":"FA8650-18-2-7861","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306230","display_name":"American Heart Association","ror":"https://ror.org/013kjyp64"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4310251122.pdf","grobid_xml":"https://content.openalex.org/works/W4310251122.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W105298322","https://openalex.org/W1970141743","https://openalex.org/W1980208272","https://openalex.org/W2018055497","https://openalex.org/W2027994226","https://openalex.org/W2034761517","https://openalex.org/W2094756095","https://openalex.org/W2095761111","https://openalex.org/W2115572397","https://openalex.org/W2122992089","https://openalex.org/W2155893237","https://openalex.org/W2289252105","https://openalex.org/W2466242877","https://openalex.org/W2471164860","https://openalex.org/W2517689844","https://openalex.org/W2544002786","https://openalex.org/W2626211758","https://openalex.org/W2792626659","https://openalex.org/W2792647449","https://openalex.org/W2798482398","https://openalex.org/W2809409253","https://openalex.org/W2899691047","https://openalex.org/W2899915146","https://openalex.org/W2906737788","https://openalex.org/W2925491732","https://openalex.org/W2950656546","https://openalex.org/W2961619211","https://openalex.org/W2980104813","https://openalex.org/W2998570630","https://openalex.org/W3015998244","https://openalex.org/W3090389586","https://openalex.org/W3113163436","https://openalex.org/W3130920634","https://openalex.org/W3159763498","https://openalex.org/W3169788481","https://openalex.org/W3190681843","https://openalex.org/W3205376812","https://openalex.org/W4239489018","https://openalex.org/W4240067093","https://openalex.org/W4251637954","https://openalex.org/W4281707342"],"related_works":["https://openalex.org/W2489934651","https://openalex.org/W108401543","https://openalex.org/W2279642117","https://openalex.org/W4300190729","https://openalex.org/W2953056293","https://openalex.org/W4200143910","https://openalex.org/W2019374455","https://openalex.org/W1975522091","https://openalex.org/W2033486618","https://openalex.org/W1576429146"],"abstract_inverted_index":{"Image":[0],"processing":[1,279],"and":[2,19,65,96,135,228,236,270,280,290],"machine":[3,281],"learning":[4,282],"applications":[5,29,176],"benefit":[6],"tremendously":[7],"from":[8,157],"hardware":[9],"acceleration.":[10],"Existing":[11],"compilers":[12],"target":[13],"either":[14],"FPGAs,":[15],"which":[16,25],"sacrifice":[17],"power":[18],"performance":[20,269],"for":[21,194],"programmability,":[22],"or":[23,86,89],"ASICs,":[24],"become":[26],"obsolete":[27],"as":[28,35,42],"change.":[30],"Programmable":[31],"domain-specific":[32,71],"accelerators,":[33],"such":[34],"coarse-grained":[36],"reconfigurable":[37,200],"arrays":[38],"(CGRAs),":[39],"have":[40,48],"emerged":[41],"a":[43,57,139,185,211,223,242,247,262,274],"promising":[44],"middle-ground,":[45],"but":[46],"they":[47,55],"traditionally":[49],"been":[50],"difficult":[51],"compiler":[52,122,150,171,263],"targets":[53],"since":[54],"use":[56,73],"different":[58,178],"memory":[59,68,94,155,162,180,197,204,249],"abstraction.":[60],"In":[61],"contrast":[62],"to":[63,83,87,125,151,160,172,177,221,264,268,295],"CPUs":[64],"GPUs,":[66],"the":[67,93,98,105,115,121,149,158,165,192,206],"hierarchies":[69],"of":[70,117,277],"accelerators":[72],"push":[74,110,154,196],"memories":[75,77,119],":":[76],"that":[78,114,250,260],"send":[79],"input":[80],"data":[81,101],"streams":[82],"computation":[84],"kernels":[85],"higher":[88],"lower":[90],"levels":[91],"in":[92,120,138,164],"hierarchy":[95],"store":[97],"resulting":[99],"output":[100],"streams.":[102],"To":[103],"address":[104,133,218],"compilation":[106],"challenge":[107],"caused":[108],"by":[109,129],"memories,":[111],"we":[112],"propose":[113],"representation":[116],"these":[118],"be":[123],"altered":[124],"directly":[126],"represent":[127],"them":[128],"combining":[130],"storage":[131],"with":[132,184,216,225],"generation":[134,219],"control":[136],"logic":[137,220],"single":[140],"structure\u2014a":[141],"unified":[142,145],"buffer.":[143],"The":[144,188],"buffer":[146,224,244],"abstraction":[147],"enables":[148],"separate":[152],"generic":[153],"optimizations":[156],"mapping":[159],"specific":[161],"implementations":[163],"backend.":[166],"This":[167],"separation":[168,189],"allows":[169],"our":[170,256,284],"map":[173],"high-level":[174],"Halide":[175],"CGRA":[179,285],"designs,":[181],"including":[182],"some":[183],"ready-valid":[186],"interface.":[187],"also":[190],"opens":[191],"opportunity":[193],"optimizing":[195],"elements":[198],"on":[199],"arrays.":[201],"Our":[202],"optimized":[203],"implementation,":[205],"Physical":[207],"Unified":[208],"Buffer,":[209],"uses":[210],"wide-fetch,":[212],"single-port":[213],"SRAM":[214],"macro":[215],"built-in":[217],"implement":[222],"two":[226,229,253],"read":[227],"write":[230],"ports.":[231,254],"It":[232],"is":[233],"18%":[234],"smaller":[235],"consumes":[237],"31%":[238],"less":[239],"energy":[240,271],"than":[241],"physical":[243],"implementation":[245],"using":[246],"dual-port":[248],"only":[251],"supports":[252],"Finally,":[255],"system":[257],"evaluation":[258],"shows":[259],"enabling":[261],"support":[265],"CGRAs":[266],"leads":[267],"benefits.":[272],"Over":[273],"wide":[275],"range":[276],"image":[278],"applications,":[283],"achieves":[286],"4.7\u00d7":[287],"better":[288,292],"runtime":[289],"3.5\u00d7":[291],"energy-efficiency":[293],"compared":[294],"an":[296],"FPGA.":[297]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
