{"id":"https://openalex.org/W4401408886","doi":"https://doi.org/10.1145/3673038.3673136","title":"The Case for Co-Designing Model Architectures with Hardware","display_name":"The Case for Co-Designing Model Architectures with Hardware","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4401408886","doi":"https://doi.org/10.1145/3673038.3673136"},"language":"en","primary_location":{"id":"doi:10.1145/3673038.3673136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3673038.3673136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-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/A5015153122","display_name":"Quentin Anthony","orcid":"https://orcid.org/0000-0002-6823-9080"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quentin Anthony","raw_affiliation_strings":["Ohio State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093817099","display_name":"Jacob Hatef","orcid":"https://orcid.org/0000-0002-1965-9169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Hatef","raw_affiliation_strings":["Ohio State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079514101","display_name":"Deepak Narayanan","orcid":"https://orcid.org/0000-0002-3020-2848"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deepak Narayanan","raw_affiliation_strings":["NVIDIA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076733732","display_name":"Stella Biderman","orcid":"https://orcid.org/0000-0001-8228-1042"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stella Biderman","raw_affiliation_strings":["EleutherAI, USA"],"affiliations":[{"raw_affiliation_string":"EleutherAI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079005032","display_name":"Stas Bekman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128771","display_name":"Contextual Change (United States)","ror":"https://ror.org/03bskcm82","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128771"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stas Bekman","raw_affiliation_strings":["Contextual AI, USA"],"affiliations":[{"raw_affiliation_string":"Contextual AI, USA","institution_ids":["https://openalex.org/I4210128771"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051882926","display_name":"Junqi Yin","orcid":"https://orcid.org/0000-0003-3843-5520"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junqi Yin","raw_affiliation_strings":["Oak Ridge National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078128277","display_name":"Aamir Shafi","orcid":"https://orcid.org/0000-0002-1924-2769"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aamir Shafi","raw_affiliation_strings":["Ohio State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["Ohio State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar Panda","raw_affiliation_strings":["Ohio State University, United States of America"],"affiliations":[{"raw_affiliation_string":"Ohio State University, United States of America","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5015153122"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.3121,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81377421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.82916259765625},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6912464499473572},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6768665313720703},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6272952556610107},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5741735100746155},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5639910697937012},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4957481324672699},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4785657227039337},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47855454683303833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4719632863998413},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4625586271286011},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4383493661880493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3838869333267212},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3758814334869385},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32371509075164795},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17881479859352112},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14702779054641724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82916259765625},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6912464499473572},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6768665313720703},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6272952556610107},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5741735100746155},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5639910697937012},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4957481324672699},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4785657227039337},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47855454683303833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4719632863998413},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4625586271286011},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4383493661880493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3838869333267212},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3758814334869385},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32371509075164795},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17881479859352112},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14702779054641724},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3673038.3673136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3673038.3673136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2895305554","https://openalex.org/W2969414999","https://openalex.org/W3043303806","https://openalex.org/W3130716829","https://openalex.org/W3204998121","https://openalex.org/W3213061620","https://openalex.org/W4281758439","https://openalex.org/W4318603275","https://openalex.org/W4321636575","https://openalex.org/W4362655426"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4360995913","https://openalex.org/W4312193868"],"abstract_inverted_index":{"While":[0],"GPUs":[1],"are":[2,19],"responsible":[3],"for":[4,64],"training":[5,52],"the":[6,14,41,47,68,83,93,96,102,106],"vast":[7],"majority":[8],"of":[9,16,50,62,71,85,95,108,129],"state-of-the-art":[10],"deep":[11,25],"learning":[12,26],"models,":[13],"implications":[15],"their":[17,72],"architecture":[18],"often":[20],"overlooked":[21],"when":[22],"designing":[23],"new":[24],"(DL)":[27],"models.":[28,74],"As":[29],"a":[30,33,60,126],"consequence,":[31],"modifying":[32],"DL":[34,51],"model":[35,87,90,112],"to":[36,40,66,116,123],"be":[37],"more":[38],"amenable":[39],"target":[42],"hardware":[43],"can":[44],"significantly":[45],"improve":[46],"runtime":[48,69],"performance":[49,70],"and":[53],"inference.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"provide":[59],"set":[61],"guidelines":[63,76],"users":[65],"maximize":[67],"transformer":[73],"These":[75],"have":[77],"been":[78],"created":[79],"by":[80],"carefully":[81],"considering":[82],"impact":[84],"various":[86],"hyperparameters":[88],"controlling":[89],"shape":[91],"on":[92,101],"efficiency":[94],"underlying":[97],"computation":[98],"kernels":[99],"executed":[100],"GPU.":[103],"We":[104],"find":[105],"throughput":[107],"models":[109,124],"with":[110,125,132],"\u201cefficient\u201d":[111],"shapes":[113],"is":[114],"up":[115],"39%":[117],"higher":[118],"while":[119],"preserving":[120],"accuracy":[121],"compared":[122],"similar":[127],"number":[128],"parameters":[130],"but":[131],"unoptimized":[133],"shapes.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}