{"id":"https://openalex.org/W4396834092","doi":"https://doi.org/10.1145/3664652","title":"An Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators","display_name":"An Open-Source ML-Based Full-Stack Optimization Framework for Machine Learning Accelerators","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4396834092","doi":"https://doi.org/10.1145/3664652"},"language":"en","primary_location":{"id":"doi:10.1145/3664652","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664652","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664652","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"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":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3664652","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084514143","display_name":"Hadi Esmaeilzadeh","orcid":"https://orcid.org/0000-0002-8548-1039"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hadi Esmaeilzadeh","raw_affiliation_strings":["University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082499242","display_name":"Soroush Ghodrati","orcid":"https://orcid.org/0000-0001-5514-8027"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soroush Ghodrati","raw_affiliation_strings":["University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073558386","display_name":"Andrew B. Kahng","orcid":"https://orcid.org/0000-0002-4490-5018"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Kahng","raw_affiliation_strings":["CSE and ECE, University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"CSE and ECE, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103036521","display_name":"Joon Kyung Kim","orcid":"https://orcid.org/0000-0003-2698-7950"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joon Kyung Kim","raw_affiliation_strings":["University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000799803","display_name":"Sean Kinzer","orcid":"https://orcid.org/0000-0002-0955-585X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Kinzer","raw_affiliation_strings":["University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004121199","display_name":"Sayak Kundu","orcid":"https://orcid.org/0000-0002-8077-1328"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayak Kundu","raw_affiliation_strings":["Electrical and Computer Engineering, University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047989184","display_name":"Rohan Mahapatra","orcid":"https://orcid.org/0000-0002-2887-9761"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Mahapatra","raw_affiliation_strings":["University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004590102","display_name":"Susmita Dey Manasi","orcid":"https://orcid.org/0000-0001-9358-6255"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susmita Dey Manasi","raw_affiliation_strings":["University of Minnesota, Minneapolis, United States"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, United States","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068714995","display_name":"Sachin S. Sapatnekar","orcid":"https://orcid.org/0000-0002-5353-2364"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sachin Sapatnekar","raw_affiliation_strings":["Electrical and Computer Engineering, Univ of Minnesota, Minneapolis, United States"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Univ of Minnesota, Minneapolis, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078035974","display_name":"Zhiang Wang","orcid":"https://orcid.org/0000-0002-6669-9702"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiang Wang","raw_affiliation_strings":["ECE, University of California San Diego, La Jolla, United States"],"affiliations":[{"raw_affiliation_string":"ECE, University of California San Diego, La Jolla, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022067893","display_name":"Ziqing Zeng","orcid":"https://orcid.org/0000-0002-6981-2299"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqing Zeng","raw_affiliation_strings":["University of Minnesota, Minneapolis, United States"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, United States","institution_ids":["https://openalex.org/I2800403580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5084514143"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":1.4682,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80577789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"29","issue":"4","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9987999796867371,"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":0.8783243894577026},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6208802461624146},{"id":"https://openalex.org/keywords/application-specific-integrated-circuit","display_name":"Application-specific integrated circuit","score":0.5992820262908936},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5846718549728394},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5593292713165283},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47677022218704224},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4536029100418091},{"id":"https://openalex.org/keywords/stack","display_name":"Stack (abstract data type)","score":0.43886247277259827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4327768087387085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40413856506347656},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3592175245285034},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34964442253112793},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16820454597473145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8783243894577026},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6208802461624146},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.5992820262908936},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5846718549728394},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5593292713165283},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47677022218704224},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4536029100418091},{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.43886247277259827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4327768087387085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40413856506347656},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3592175245285034},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34964442253112793},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16820454597473145}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664652","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664652","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664652","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"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":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3664652","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664652","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3664652","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"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":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.4099999964237213,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G4790131527","display_name":null,"funder_award_id":"FA8650-20-2-7009","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"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/W4396834092.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W347636100","https://openalex.org/W1656197734","https://openalex.org/W1990505905","https://openalex.org/W2076350013","https://openalex.org/W2162385899","https://openalex.org/W2170382128","https://openalex.org/W2261808795","https://openalex.org/W2289252105","https://openalex.org/W2889669826","https://openalex.org/W2963114857","https://openalex.org/W3013057549","https://openalex.org/W3034870003","https://openalex.org/W3040394052","https://openalex.org/W3103682307","https://openalex.org/W3110928049","https://openalex.org/W3127676525","https://openalex.org/W3201124836","https://openalex.org/W3210800143","https://openalex.org/W3213528054","https://openalex.org/W4200413004","https://openalex.org/W4200520905","https://openalex.org/W4233056867","https://openalex.org/W4280634595","https://openalex.org/W4288083644","https://openalex.org/W4297822298","https://openalex.org/W4312121077","https://openalex.org/W4313476040","https://openalex.org/W4379115897"],"related_works":["https://openalex.org/W3005710104","https://openalex.org/W3092334294","https://openalex.org/W2111062328","https://openalex.org/W2108386578","https://openalex.org/W1572417577","https://openalex.org/W91363257","https://openalex.org/W2142450926","https://openalex.org/W3139655666","https://openalex.org/W2118185763","https://openalex.org/W1550409889"],"abstract_inverted_index":{"Parameterizable":[0],"machine":[1],"learning":[2,125],"(ML)":[3],"accelerators":[4],"are":[5],"the":[6,119],"product":[7],"of":[8,60,92,122],"recent":[9],"breakthroughs":[10],"in":[11,131],"ML.":[12],"To":[13],"fully":[14,78],"enable":[15],"their":[16],"design":[17],"space":[18],"exploration":[19],"(DSE),":[20],"we":[21],"propose":[22],"a":[23,40,57,77,133,139],"physical-design-driven,":[24],"learning-based":[25],"prediction":[26,116],"framework":[27,75],"for":[28,118],"hardware-accelerated":[29],"deep":[30,124],"neural":[31],"network":[32],"(DNN)":[33],"and":[34,47,64,70,85,94,107,129,138],"non-DNN":[35],"ML":[36],"algorithms.":[37],"It":[38],"adopts":[39],"unified":[41],"approach":[42,102],"that":[43,100],"combines":[44],"power,":[45],"performance,":[46],"area":[48],"(PPA)":[49],"analysis":[50],"with":[51,110],"frontend":[52],"performance":[53],"simulation,":[54],"thereby":[55],"achieving":[56],"realistic":[58],"estimation":[59],"both":[61,132],"backend":[62,84,95,105],"PPA":[63,106],"system":[65,86,108],"metrics":[66,87,109],"such":[67],"as":[68],"runtime":[69],"energy.":[71],"In":[72],"addition,":[73],"our":[74,101],"includes":[76],"automated":[79,90],"DSE":[80],"technique,":[81],"which":[82],"optimizes":[83],"through":[88],"an":[89,111],"search":[91],"architectural":[93],"parameters.":[96],"Experimental":[97],"studies":[98],"show":[99],"consistently":[103],"predicts":[104],"average":[112],"7%":[113],"or":[114],"less":[115],"error":[117],"ASIC":[120],"implementation":[121],"two":[123],"accelerator":[126],"platforms,":[127],"VTA":[128],"VeriGOOD-ML,":[130],"commercial":[134],"12":[135],"nm":[136,142],"process":[137],"research-oriented":[140],"45":[141],"process.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
